1 code implementation • 3 Jun 2024 • Tianyu Huang, Yihan Zeng, Hui Li, WangMeng Zuo, Rynson W. H. Lau
One solution is to animate 3D scenes with physics-based simulation, and the other is to learn the deformation of static 3D objects with the distillation of video generative models.
1 code implementation • 30 May 2024 • Zixian Guo, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, WangMeng Zuo
Learning a skill generally relies on both practical experience by doer and insightful high-level guidance by instructor.
1 code implementation • 28 May 2024 • Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen
Nevertheless, due to the discrete nature of texts, the input gradient of LLMs struggles to precisely reflect the magnitude of loss change that results from token replacements in the prompt, leading to limited attack success rates against safety-aligned LLMs, even in the white-box setting.
no code implementations • 14 May 2024 • Wei Lian, Zhesen Cui, Fei Ma, Hang Pan, WangMeng Zuo
In many applications, the demand arises for algorithms capable of aligning partially overlapping point sets while remaining invariant to the corresponding transformations.
1 code implementation • 9 May 2024 • Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hongzhi Zhang, Lei Zhang, WangMeng Zuo
In this work, we present MasterWeaver, a test-time tuning-free method designed to generate personalized images with both faithful identity fidelity and flexible editability.
2 code implementations • 3 May 2024 • Zhilu Zhang, Ruohao Wang, Hongzhi Zhang, WangMeng Zuo
In addition, we further take multiple zoomed observations to explore self-supervised RefSR, and present a progressive fusion scheme for the effective utilization of reference images.
1 code implementation • 26 Apr 2024 • Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, WangMeng Zuo
To address this challenge, we introduce Multi-View Virtual Try-ON (MV-VTON), which aims to reconstruct the dressing results of a person from multiple views using the given clothes.
no code implementations • 25 Apr 2024 • Zitong Huang, Ze Chen, Bowen Dong, Chaoqi Liang, Erjin Zhou, WangMeng Zuo
Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models.
1 code implementation • 17 Apr 2024 • Xin Li, Kun Yuan, Yajing Pei, Yiting Lu, Ming Sun, Chao Zhou, Zhibo Chen, Radu Timofte, Wei Sun, HaoNing Wu, ZiCheng Zhang, Jun Jia, Zhichao Zhang, Linhan Cao, Qiubo Chen, Xiongkuo Min, Weisi Lin, Guangtao Zhai, Jianhui Sun, Tianyi Wang, Lei LI, Han Kong, Wenxuan Wang, Bing Li, Cheng Luo, Haiqiang Wang, Xiangguang Chen, Wenhui Meng, Xiang Pan, Huiying Shi, Han Zhu, Xiaozhong Xu, Lei Sun, Zhenzhong Chen, Shan Liu, Fangyuan Kong, Haotian Fan, Yifang Xu, Haoran Xu, Mengduo Yang, Jie zhou, Jiaze Li, Shijie Wen, Mai Xu, Da Li, Shunyu Yao, Jiazhi Du, WangMeng Zuo, Zhibo Li, Shuai He, Anlong Ming, Huiyuan Fu, Huadong Ma, Yong Wu, Fie Xue, Guozhi Zhao, Lina Du, Jie Guo, Yu Zhang, huimin zheng, JunHao Chen, Yue Liu, Dulan Zhou, Kele Xu, Qisheng Xu, Tao Sun, Zhixiang Ding, Yuhang Hu
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
1 code implementation • 12 Apr 2024 • Rongjian Xu, Zhilu Zhang, Renlong Wu, WangMeng Zuo
Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments.
2 code implementations • 11 Apr 2024 • Junyi Li, Zhilu Zhang, WangMeng Zuo
For channel self-attention, we observe that it may leak the blind-spot information when the channel number is greater than spatial size in the deep layers of multi-scale architectures.
1 code implementation • 9 Apr 2024 • Xiaoyu Liu, Yuxiang Wei, Ming Liu, Xianhui Lin, Peiran Ren, Xuansong Xie, WangMeng Zuo
The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.
1 code implementation • 8 Apr 2024 • Jiaxiu Jiang, Yabo Zhang, Kailai Feng, Xiaohe Wu, WangMeng Zuo
Customized text-to-image generation aims to synthesize instantiations of user-specified concepts and has achieved unprecedented progress in handling individual concept.
1 code implementation • 8 Apr 2024 • Minheng Ni, Yeli Shen, Lei Zhang, WangMeng Zuo
To mitigate the negative implications of harmful images on research, we create a transparent and public dataset, AltBear, which expresses harmful information using teddy bears instead of humans.
no code implementations • 7 Apr 2024 • Binghui Chen, Wenyu Li, Yifeng Geng, Xuansong Xie, WangMeng Zuo
Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes.
no code implementations • 7 Apr 2024 • Renlong Wu, Zhilu Zhang, Yu Yang, WangMeng Zuo
In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview.
1 code implementation • 17 Mar 2024 • Renlong Wu, Zhilu Zhang, Shuohao Zhang, Longfei Gou, Haobin Chen, Lei Zhang, Hao Chen, WangMeng Zuo
On the other hand, in order to enhance the desmoking performance, we further feed the valuable information from PS frame into models, where a masking strategy and a regularization term are presented to avoid trivial solutions.
no code implementations • 12 Mar 2024 • Runmin Cong, Ronghui Sheng, Hao Wu, Yulan Guo, Yunchao Wei, WangMeng Zuo, Yao Zhao, Sam Kwong
On the one hand, the low-level detail embedding module is designed to supplement high-frequency color information of depth features in a residual mask manner at the low-level stages.
1 code implementation • 9 Mar 2024 • Chunwei Tian, Menghua Zheng, Tiancai Jiao, WangMeng Zuo, Yanning Zhang, Chia-Wen Lin
Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal.
1 code implementation • 8 Mar 2024 • Yabo Zhang, Yuxiang Wei, Xianhui Lin, Zheng Hui, Peiran Ren, Xuansong Xie, Xiangyang Ji, WangMeng Zuo
Different from conventional T2V sampling (i. e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating.
1 code implementation • 4 Mar 2024 • Zhengyao Lv, Yuxiang Wei, WangMeng Zuo, Kwan-Yee K. Wong
Extensive experiments demonstrate that our approach performs favorably in terms of visual quality, semantic consistency, and layout alignment.
no code implementations • 26 Feb 2024 • Bowen Dong, Guanglei Yang, WangMeng Zuo, Lei Zhang
Empirical investigations on the adaptation of existing frameworks to vanilla ViT reveal that incorporating visual adapters into ViTs or fine-tuning ViTs with distillation terms is advantageous for enhancing the segmentation capability of novel classes.
1 code implementation • 24 Feb 2024 • Chunwei Tian, Xuanyu Zhang, Jia Ren, WangMeng Zuo, Yanning Zhang, Chia-Wen Lin
The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information, which is complementary with a upper network for image super-resolution.
1 code implementation • 7 Feb 2024 • Lijun Li, Bowen Dong, Ruohui Wang, Xuhao Hu, WangMeng Zuo, Dahua Lin, Yu Qiao, Jing Shao
In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount.
1 code implementation • 2 Feb 2024 • Jian Liu, Xiaoshui Huang, Tianyu Huang, Lu Chen, Yuenan Hou, Shixiang Tang, Ziwei Liu, Wanli Ouyang, WangMeng Zuo, Junjun Jiang, Xianming Liu
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e. g., text, image, video, audio and 3D.
1 code implementation • 3 Jan 2024 • Zitong Huang, Ze Chen, Zhixing Chen, Erjin Zhou, Xinxing Xu, Rick Siow Mong Goh, Yong liu, WangMeng Zuo, ChunMei Feng
When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge.
2 code implementations • 1 Jan 2024 • Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, WangMeng Zuo
It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments.
1 code implementation • 28 Dec 2023 • Wan Xu, Tianyu Huang, Tianyu Qu, Guanglei Yang, Yiwen Guo, WangMeng Zuo
Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.
Dimensionality Reduction Few-Shot Class-Incremental Learning +2
1 code implementation • 28 Dec 2023 • Jingbo Lin, Zhilu Zhang, Yuxiang Wei, Dongwei Ren, Dongsheng Jiang, WangMeng Zuo
To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration.
1 code implementation • 26 Dec 2023 • Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, WangMeng Zuo
Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios.
1 code implementation • 19 Dec 2023 • Chun-Mei Feng, Yang Bai, Tao Luo, Zhen Li, Salman Khan, WangMeng Zuo, Xinxing Xu, Rick Siow Mong Goh, Yong liu
By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair.
1 code implementation • 19 Dec 2023 • Yufei Cai, Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hu Han, WangMeng Zuo
To decouple irrelevant attributes (i. e., background and pose) from the subject embedding, we further present several attribute mappers that encode each image as several image-specific subject-unrelated embeddings.
1 code implementation • 11 Dec 2023 • Tianyu Huang, Yihan Zeng, Zhilu Zhang, Wan Xu, Hang Xu, Songcen Xu, Rynson W. H. Lau, WangMeng Zuo
The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures.
no code implementations • 29 Oct 2023 • Yuanze Li, Haolin Wang, Shihao Yuan, Ming Liu, Debin Zhao, Yiwen Guo, Chen Xu, Guangming Shi, WangMeng Zuo
Existing industrial anomaly detection (IAD) methods predict anomaly scores for both anomaly detection and localization.
no code implementations • 24 Oct 2023 • Qing Miao, Xiaohe Wu, Chao Xu, Yanli Ji, WangMeng Zuo, Yiwen Guo, Zhaopeng Meng
By incorporating auxiliary information from CLIP and utilizing prompt fine-tuning, we effectively eliminate noisy samples from the clean set and mitigate confirmation bias during training.
1 code implementation • 23 Oct 2023 • Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chaoyu Feng, Xiaotao Wang, Lei Lei, WangMeng Zuo
Real-world image de-weathering aims at removing various undesirable weather-related artifacts.
1 code implementation • 16 Oct 2023 • Chunwei Tian, Menghua Zheng, WangMeng Zuo, Shichao Zhang, Yanning Zhang, Chia-Wen Ling
To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes.
1 code implementation • 12 Oct 2023 • Zehao Wang, Yiwen Guo, Qizhang Li, Guanglei Yang, WangMeng Zuo
Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i. e.}, increasing the amplitude of augmentation carefully to avoid degrading some data too much and doing harm to the model performance.
no code implementations • 11 Oct 2023 • Chaoqi Liang, Weiqiang Bai, Lifeng Qiao, Yuchen Ren, Jianle Sun, Peng Ye, Hongliang Yan, Xinzhu Ma, WangMeng Zuo, Wanli Ouyang
To address this research gap, we first conducted a series of exploratory experiments and gained several insightful observations: 1) In the fine-tuning phase of downstream tasks, when using K-mer overlapping tokenization instead of K-mer non-overlapping tokenization, both overlapping and non-overlapping pretraining weights show consistent performance improvement. 2) During the pre-training process, using K-mer overlapping tokenization quickly produces clear K-mer embeddings and reduces the loss to a very low level, while using K-mer non-overlapping tokenization results in less distinct embeddings and continuously decreases the loss.
1 code implementation • 9 Oct 2023 • Yang Bai, Xinxing Xu, Yong liu, Salman Khan, Fahad Khan, WangMeng Zuo, Rick Siow Mong Goh, Chun-Mei Feng
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption.
Ranked #1 on Image Retrieval on CIRR
1 code implementation • 3 Oct 2023 • Zhilu Zhang, Haoyu Wang, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo
The color component is estimated from aligned multi-exposure images, while the structure one is generated through a structure-focused network that is supervised by the color component and an input reference (\eg, medium-exposure) image.
no code implementations • 29 Sep 2023 • Tianyu Huang, Yihan Zeng, Bowen Dong, Hang Xu, Songcen Xu, Rynson W. H. Lau, WangMeng Zuo
To this end, an NTFGen module is proposed to model general text latent code in noisy fields.
1 code implementation • ICCV 2023 • Xiaoyu Liu, Ming Liu, Junyi Li, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo
In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).
1 code implementation • ICCV 2023 • Zhicun Yin, Ming Liu, Xiaoming Li, Hui Yang, Longan Xiao, WangMeng Zuo
To evaluate our proposed MetaF2N, we have collected a real-world low-quality dataset with one or multiple faces in each image, and our MetaF2N achieves superior performance on both synthetic and real-world datasets.
1 code implementation • 13 Sep 2023 • Dongwei Ren, Wei Shang, Yi Yang, WangMeng Zuo
To aggregate long-term sharp features from detected sharp frames, we utilize a global Transformer with multi-scale matching capability.
no code implementations • 4 Sep 2023 • Yuanshuo Cheng, Mingwen Shao, Yecong Wan, Yuanjian Qiao, WangMeng Zuo, Deyu Meng
To empower the framework for eliminating diverse degradations, we devise a Sequence-wise Adaptive Degradation Estimator (SADE) to estimate degradation features for the input corrupted video.
no code implementations • 31 Aug 2023 • Minheng Ni, Yabo Zhang, Kailai Feng, Xiaoming Li, Yiwen Guo, WangMeng Zuo
In this work, we introduce a novel Referring Diffusional segmentor (Ref-Diff) for this task, which leverages the fine-grained multi-modal information from generative models.
1 code implementation • 27 Aug 2023 • Mingshuai Yao, Yabo Zhang, Xianhui Lin, Xiaoming Li, WangMeng Zuo
In this paper, we propose a VQGAN-based framework (i. e., VQ-Font) to enhance glyph fidelity through token prior refinement and structure-aware enhancement.
1 code implementation • 21 Aug 2023 • Jian Zou, Tianyu Huang, Guanglei Yang, Zhenhua Guo, WangMeng Zuo
The extension makes it possible to back-project the informative features, obtained by fusing features from both modalities, into their native modalities to reconstruct the multiple masked inputs.
no code implementations • 20 Aug 2023 • Yunlu Yan, Chun-Mei Feng, Mang Ye, WangMeng Zuo, Ping Li, Rick Siow Mong Goh, Lei Zhu, C. L. Philip Chen
Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype.
1 code implementation • ICCV 2023 • Chun-Mei Feng, Kai Yu, Yong liu, Salman Khan, WangMeng Zuo
In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT).
1 code implementation • ICCV 2023 • Chun-Mei Feng, Kai Yu, Nian Liu, Xinxing Xu, Salman Khan, WangMeng Zuo
However, the performance of the global model is often hampered by non-i. i. d.
1 code implementation • 24 Jul 2023 • Mingwen Shao, Lingzhuang Meng, Yuanjian Qiao, Lixu Zhang, WangMeng Zuo
Specifically, we augment the latent codes of the inferred member data with LCA and use them as guidance for SD.
no code implementations • 21 Jul 2023 • Qizhang Li, Yiwen Guo, Xiaochen Yang, WangMeng Zuo, Hao Chen
Our ICLR work advocated for enhancing transferability in adversarial examples by incorporating a Bayesian formulation into model parameters, which effectively emulates the ensemble of infinitely many deep neural networks, while, in this paper, we introduce a novel extension by incorporating the Bayesian formulation into the model input as well, enabling the joint diversification of both the model input and model parameters.
1 code implementation • 30 Jun 2023 • Renlong Wu, Zhilu Zhang, Shuohao Zhang, Hongzhi Zhang, WangMeng Zuo
The main challenge of BurstSR is to effectively combine the complementary information from input frames, while existing methods still struggle with it.
no code implementations • 28 Jun 2023 • Jie Ning, Jiebao Sun, Yao Li, Zhichang Guo, WangMeng Zuo
Thus, we further propose an indicator to measure the local similarity of models, called robustness similitude.
1 code implementation • CVPR 2023 • Yuxiang Wei, Zhilong Ji, Xiaohe Wu, Jinfeng Bai, Lei Zhang, WangMeng Zuo
Despite the progress in semantic image synthesis, it remains a challenging problem to generate photo-realistic parts from input semantic map.
2 code implementations • ICCV 2023 • Wei Shang, Dongwei Ren, Chaoyu Feng, Xiaotao Wang, Lei Lei, WangMeng Zuo
In this paper, we propose a Self-supervised learning framework for Dual reversed RS distortions Correction (SelfDRSC), where a DRSC network can be learned to generate a high framerate GS video only based on dual RS images with reversed distortions.
1 code implementation • 22 May 2023 • Yabo Zhang, Yuxiang Wei, Dongsheng Jiang, Xiaopeng Zhang, WangMeng Zuo, Qi Tian
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling.
2 code implementations • NeurIPS 2023 • Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen
In particular, the proposed method, named intermediate-level perturbation decay (ILPD), encourages the intermediate-level perturbation to be in an effective adversarial direction and to possess a great magnitude simultaneously.
no code implementations • 3 Apr 2023 • Yabo Zhang, ZiHao Wang, Jun Hao Liew, Jingjia Huang, Manyu Zhu, Jiashi Feng, WangMeng Zuo
In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs.
1 code implementation • CVPR 2023 • Chun-Mei Feng, Bangjun Li, Xinxing Xu, Yong liu, Huazhu Fu, WangMeng Zuo
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy.
3 code implementations • CVPR 2023 • Wei Shang, Dongwei Ren, Yi Yang, Hongzhi Zhang, Kede Ma, WangMeng Zuo
Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1. 5 dB in terms of PSNR.
1 code implementation • CVPR 2023 • Junyi Li, Zhilu Zhang, Xiaoyu Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, WangMeng Zuo
And we extend the blind-spot network to a blind-neighborhood network (BNN) for providing supervision on flat areas.
1 code implementation • CVPR 2023 • Xiaoming Li, WangMeng Zuo, Chen Change Loy
To restrict the generative space of StyleGAN so that it obeys the structure of characters yet remains flexible in handling different font styles, we store the discrete features for each character in a codebook.
no code implementations • 12 Mar 2023 • Bowen Dong, Jiaxi Gu, Jianhua Han, Hang Xu, WangMeng Zuo
To improve the open-world segmentation ability, we leverage omni-supervised data (i. e., panoptic segmentation data, object detection data, and image-text pairs data) into training, thus enriching the open-world segmentation ability and achieving better segmentation accuracy.
1 code implementation • ICCV 2023 • Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, WangMeng Zuo
In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation.
1 code implementation • 10 Feb 2023 • Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen
In this paper, by contrast, we opt for the diversity in substitute models and advocate to attack a Bayesian model for achieving desirable transferability.
no code implementations • CVPR 2023 • Minheng Ni, Xiaoming Li, WangMeng Zuo
Language-guided image inpainting aims to fill the defective regions of an image under the guidance of text while keeping the non-defective regions unchanged.
1 code implementation • CVPR 2023 • Yue Cao, Ming Liu, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo
Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling.
Ranked #1 on Image Denoising on ELD SonyA7S2 x200
no code implementations • 27 Dec 2022 • Bo Chen, Zhiwei Hu, Zhilong Ji, Jinfeng Bai, WangMeng Zuo
The main challenge of this task is to understand the visual and linguistic content simultaneously and to find the referred object accurately among all instances in the image.
1 code implementation • IEEE Transactions on Image Processing 2022 • Shuguang Dou, Cairong Zhao, Xinyang Jiang, Shanshan Zhang, Wei-Shi Zheng, WangMeng Zuo
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #3 on Person Re-Identification on Occluded-DukeMTMC
1 code implementation • 13 Dec 2022 • Qinghe Wang, Lijie Liu, Miao Hua, Pengfei Zhu, WangMeng Zuo, QinGhua Hu, Huchuan Lu, Bing Cao
We blend the semantic layouts of source head and source body, and then inpaint the transition region by the semantic layout generator, achieving a coarse-grained head swapping.
1 code implementation • 10 Dec 2022 • Ruohao Wang, Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chun-Mei Feng, Lei Zhang, WangMeng Zuo
On the other hand, alignment algorithms in existing VSR methods perform poorly for real-world videos, leading to unsatisfactory results.
no code implementations • 8 Dec 2022 • Wenxin Wang, Boyun Li, Yuanbiao Gou, Peng Hu, WangMeng Zuo, Xi Peng
To tackle the first challenge, we proposed a Degradation Relationship Index (DRI) which is defined as the mean drop rate difference in the validation loss between two models which are respectively trained using the anchor degradation and the mixture of the anchor and the auxiliary degradations.
2 code implementations • 26 Nov 2022 • Yu Li, Dongwei Ren, Xinya Shu, WangMeng Zuo
First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images.
1 code implementation • CVPR 2023 • Zixian Guo, Bowen Dong, Zhilong Ji, Jinfeng Bai, Yiwen Guo, WangMeng Zuo
Nonetheless, visual data (e. g., images) is by default prerequisite for learning prompts in existing methods.
Contrastive Learning Multi-label Image Recognition with Partial Labels
1 code implementation • 14 Nov 2022 • Zhilu Zhang, Rongjian Xu, Ming Liu, Zifei Yan, WangMeng Zuo
By learning in a collaborative manner, the deblurring and denoising tasks in our method can benefit each other.
1 code implementation • 20 Oct 2022 • Marcos V. Conde, Radu Timofte, Yibin Huang, Jingyang Peng, Chang Chen, Cheng Li, Eduardo Pérez-Pellitero, Fenglong Song, Furui Bai, Shuai Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, Yu Zhu, Chenghua Li, Yingying Jiang, Yong A, Peisong Wang, Cong Leng, Jian Cheng, Xiaoyu Liu, Zhicun Yin, Zhilu Zhang, Junyi Li, Ming Liu, WangMeng Zuo, Jun Jiang, Jinha Kim, Yue Zhang, Beiji Zou, Zhikai Zong, Xiaoxiao Liu, Juan Marín Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Furkan Kınlı, Barış Özcan, Furkan Kıraç, Li Leyi, SM Nadim Uddin, Dipon Kumar Ghosh, Yong Ju Jung
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
1 code implementation • 15 Oct 2022 • Xiaoming Li, Shiguang Zhang, Shangchen Zhou, Lei Zhang, WangMeng Zuo
Generally, it is a challenging and intractable task to improve the photo-realistic performance of blind restoration and adaptively handle the generic and specific restoration scenarios with a single unified model.
1 code implementation • 13 Oct 2022 • Minheng Ni, Zitong Huang, Kailai Feng, WangMeng Zuo
Given a class label, the language model is used to generate a full description of a scene with a target object, and the text-to-image model deployed to generate a photo-realistic image.
1 code implementation • 3 Oct 2022 • Bowen Dong, Pan Zhou, Shuicheng Yan, WangMeng Zuo
For better effectiveness, we divide prompts into two groups: 1) a shared prompt for the whole long-tailed dataset to learn general features and to adapt a pretrained model into target domain; and 2) group-specific prompts to gather group-specific features for the samples which have similar features and also to empower the pretrained model with discrimination ability.
Ranked #1 on Long-tail Learning on CIFAR-100-LT (ρ=100) (using extra training data)
1 code implementation • 3 Oct 2022 • Xiaoming Li, Chaofeng Chen, Xianhui Lin, WangMeng Zuo, Lei Zhang
Notably, LQ face images, which may have the same degradation process as natural images, can be robustly restored with photo-realistic textures by exploiting their strong structural priors.
1 code implementation • ICCV 2023 • Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang, Rynson W. H. Lau, Wanli Ouyang, WangMeng Zuo
To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification.
Ranked #3 on Training-free 3D Point Cloud Classification on ScanObjectNN (using extra training data)
1 code implementation • 26 Sep 2022 • Chunwei Tian, Menghua Zheng, WangMeng Zuo, Bob Zhang, Yanning Zhang, David Zhang
In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i. e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB).
1 code implementation • 26 Sep 2022 • Chunwei Tian, Yanning Zhang, WangMeng Zuo, Chia-Wen Lin, David Zhang, Yixuan Yuan
To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN.
1 code implementation • ACMMM 2022 • Yudong Liang, Bin Wang, Wenqi Ren, Jiaying Liu, Wenjian Wang, WangMeng Zuo
In various real-world image enhancement applications, the degradations are always non-uniform or non-homogeneous and diverse, which challenges most deep networks with fixed parameters during the inference phase.
Ranked #14 on Image Dehazing on SOTS Indoor
no code implementations • 8 Aug 2022 • Hannan Lu, Zhi Tian, Lirong Yang, Haibing Ren, WangMeng Zuo
The compact instance stream effectively improves the segmentation accuracy of the unseen pixels, while fusing two streams with the adaptive routing map leads to an overall performance boost.
1 code implementation • 25 Jul 2022 • Zitong Huang, Yiping Bao, Bowen Dong, Erjin Zhou, WangMeng Zuo
Generally, with given pseudo ground-truths generated from the well-trained WSOD network, we propose a two-module iterative training algorithm to refine pseudo labels and supervise better object detector progressively.
1 code implementation • 21 Jul 2022 • Ming Liu, Yuxiang Wei, Xiaohe Wu, WangMeng Zuo, Lei Zhang
Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality.
1 code implementation • 18 Jul 2022 • Qiying Yu, Jieming Lou, Xianyuan Zhan, Qizhang Li, WangMeng Zuo, Yang Liu, Jingjing Liu
Contrastive learning (CL) has recently been applied to adversarial learning tasks.
1 code implementation • 18 Jul 2022 • Yabo Zhang, Mingshuai Yao, Yuxiang Wei, Zhilong Ji, Jinfeng Bai, WangMeng Zuo
In this paper, we present a novel one-shot generative domain adaption method, i. e., DiFa, for diverse generation and faithful adaptation.
1 code implementation • 13 Jul 2022 • Tianyu Huang, Bowen Dong, Jiaying Lin, Xiaohui Liu, Rynson W. H. Lau, WangMeng Zuo
Mirror detection aims to identify the mirror regions in the given input image.
1 code implementation • 12 Jul 2022 • Haolin Wang, Jiawei Zhang, Ming Liu, Xiaohe Wu, WangMeng Zuo
In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass.
1 code implementation • 16 Jun 2022 • Xin Zhong, Zhaoyi Yan, Jing Qin, WangMeng Zuo, Weigang Lu
However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information.
1 code implementation • 8 Jun 2022 • Pengju Liu, Hongzhi Zhang, Jinghui Wang, Yuzhi Wang, Dongwei Ren, WangMeng Zuo
In particular, we take well-trained CBDNet, NBNet, HINet, Uformer and GMSNet into denoiser pool, and a U-Net is adopted to predict pixel-wise weighting maps to fuse these denoisers.
1 code implementation • 29 May 2022 • Chunwei Tian, Yixuan Yuan, Shichao Zhang, Chia-Wen Lin, WangMeng Zuo, David Zhang
In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR).
1 code implementation • 23 May 2022 • Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community.
no code implementations • 28 Apr 2022 • Chunwei Tian, Xuanyu Zhang, Jerry Chun-Wei Lin, WangMeng Zuo, Yanning Zhang, Chia-Wen Lin
Second, we present popular architectures for GANs in big and small samples for image applications.
1 code implementation • 26 Apr 2022 • Yu Li, Yaling Yi, Dongwei Ren, Qince Li, WangMeng Zuo
Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the sharp image.
2 code implementations • 20 Apr 2022 • Ren Yang, Radu Timofte, Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen, Youcheng Ben, Xiao Zhou, Chen Fu, Pei Cheng, Gang Yu, Junyi Li, Renlong Wu, Zhilu Zhang, Wei Shang, Zhengyao Lv, Yunjin Chen, Mingcai Zhou, Dongwei Ren, Kai Zhang, WangMeng Zuo, Pavel Ostyakov, Vyal Dmitry, Shakarim Soltanayev, Chervontsev Sergey, Zhussip Magauiya, Xueyi Zou, Youliang Yan, Pablo Navarrete Michelini, Yunhua Lu, Diankai Zhang, Shaoli Liu, Si Gao, Biao Wu, Chengjian Zheng, Xiaofeng Zhang, Kaidi Lu, Ning Wang, Thuong Nguyen Canh, Thong Bach, Qing Wang, Xiaopeng Sun, Haoyu Ma, Shijie Zhao, Junlin Li, Liangbin Xie, Shuwei Shi, Yujiu Yang, Xintao Wang, Jinjin Gu, Chao Dong, Xiaodi Shi, Chunmei Nian, Dong Jiang, Jucai Lin, Zhihuai Xie, Mao Ye, Dengyan Luo, Liuhan Peng, Shengjie Chen, Qian Wang, Xin Liu, Boyang Liang, Hang Dong, Yuhao Huang, Kai Chen, Xingbei Guo, Yujing Sun, Huilei Wu, Pengxu Wei, Yulin Huang, Junying Chen, Ik Hyun Lee, Sunder Ali Khowaja, Jiseok Yoon
This challenge includes three tracks.
no code implementations • CVPR 2022 • Yue Cao, Zhaolin Wan, Dongwei Ren, Zifei Yan, WangMeng Zuo
Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i. e., outliers) from unlabeled data.
1 code implementation • 12 Apr 2022 • Junyi Li, Xiaohe Wu, Zhenxing Niu, WangMeng Zuo
However, BiRNN is intrinsically offline because it uses backward recurrent modules to propagate from the last to current frames, which causes high latency and large memory consumption.
1 code implementation • 12 Apr 2022 • Zhaohui Zheng, Rongguang Ye, Qibin Hou, Dongwei Ren, Ping Wang, WangMeng Zuo, Ming-Ming Cheng
Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
1 code implementation • CVPR 2022 • Yupeng Shi, Xiao Liu, Yuxiang Wei, Zhongqin Wu, WangMeng Zuo
Semantic image synthesis is a challenging task with many practical applications.
1 code implementation • 4 Apr 2022 • Ming Liu, Jianan Pan, Zifei Yan, WangMeng Zuo, Lei Zhang
Meanwhile, diverse testing sets are also provided with different types of reflection and scenes.
1 code implementation • CVPR 2022 • Zhengyao Lv, Xiaoming Li, Zhenxing Niu, Bing Cao, WangMeng Zuo
Obviously, a fine-grained part-level semantic layout will benefit object details generation, and it can be roughly inferred from an object's shape.
1 code implementation • 21 Mar 2022 • Yiwen Guo, Qizhang Li, WangMeng Zuo, Hao Chen
This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples.
1 code implementation • 14 Mar 2022 • Bowen Dong, Pan Zhou, Shuicheng Yan, WangMeng Zuo
The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired.
no code implementations • 6 Mar 2022 • Yuanze Li, Yiwen Guo, Qizhang Li, Hongzhi Zhang, WangMeng Zuo
Despite the remarkable progress, the challenge of optimally learning different tasks simultaneously remains to be explored.
2 code implementations • 2 Mar 2022 • Zhilu Zhang, Ruohao Wang, Hongzhi Zhang, Yunjin Chen, WangMeng Zuo
For this purpose, we take the telephoto image instead of an additional high-resolution image as the supervision information and select a center patch from it as the reference to super-resolve the corresponding short-focus image patch.
no code implementations • 10 Feb 2022 • Minheng Ni, Chenfei Wu, Haoyang Huang, Daxin Jiang, WangMeng Zuo, Nan Duan
Language guided image inpainting aims to fill in the defective regions of an image under the guidance of text while keeping non-defective regions unchanged.
no code implementations • 24 Dec 2021 • Jize Zhang, Haolin Wang, Xiaohe Wu, WangMeng Zuo
Existing unpaired low-light image enhancement approaches prefer to employ the two-way GAN framework, in which two CNN generators are deployed for enhancement and degradation separately.
no code implementations • 29 Sep 2021 • Fangcen Liu, Chenqiang Gao, Fang Chen, Deyu Meng, WangMeng Zuo, Xinbo Gao
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
1 code implementation • ICCV 2021 • Binghui Chen, Zhaoyi Yan, Ke Li, Pengyu Li, Biao Wang, WangMeng Zuo, Lei Zhang
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
1 code implementation • ICCV 2021 • Zhilu Zhang, Haolin Wang, Ming Liu, Ruohao Wang, Jiawei Zhang, WangMeng Zuo
To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it.
1 code implementation • ICCV 2021 • Yuxiang Wei, Yupeng Shi, Xiao Liu, Zhilong Ji, Yuan Gao, Zhongqin Wu, WangMeng Zuo
It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation.
1 code implementation • 13 Aug 2021 • Fang Chen, Chenqiang Gao, Fangcen Liu, Yue Zhao, Yuxi Zhou, Deyu Meng, WangMeng Zuo
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
1 code implementation • ICCV 2021 • Bowen Dong, Zitong Huang, Yuelin Guo, Qilong Wang, Zhenxing Niu, WangMeng Zuo
In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset.
1 code implementation • 8 Jul 2021 • Zhaoyi Yan, Ruimao Zhang, Hongzhi Zhang, Qingfu Zhang, WangMeng Zuo
One of the main issues in this task is how to handle the dramatic scale variations of pedestrians caused by the perspective effect.
no code implementations • CVPR 2021 • Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang, Xiangyang Ji
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
no code implementations • CVPR 2021 • Wenyu Li, Tianchu Guo, Pengyu Li, Binghui Chen, Biao Wang, WangMeng Zuo, Lei Zhang
In this paper, we propose a novel face recognition method, named VirFace, to effectively apply the unlabeled shallow data for face recognition.
1 code implementation • 25 Apr 2021 • Dongsheng Wang, Chaohao Xie, Shaohui Liu, Zhenxing Niu, WangMeng Zuo
In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits.
1 code implementation • CVPR 2021 • Zhengyao Lv, Xiaoming Li, Xin Li, Fu Li, Tianwei Lin, Dongliang He, WangMeng Zuo
In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style.
no code implementations • 31 Mar 2021 • Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang, Xiangyang Ji
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
1 code implementation • 25 Mar 2021 • Chunwei Tian, Yong Xu, WangMeng Zuo, Chia-Wen Lin, David Zhang
In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution.
1 code implementation • 25 Mar 2021 • Zhi Wang, Yiwen Guo, WangMeng Zuo
In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities.
1 code implementation • 18 Mar 2021 • Yue Cao, Xiaohe Wu, Shuran Qi, Xiao Liu, Zhongqin Wu, WangMeng Zuo
To begin with, the pre-trained denoiser is used to generate the pseudo clean images for the test images.
1 code implementation • 9 Mar 2021 • Chaohao Xie, Dongwei Ren, Lei Wang, WangMeng Zuo
For learning pseudo mask generator from the auxiliary dataset, we present a bi-level optimization formulation.
2 code implementations • CVPR 2022 • Zhaohui Zheng, Rongguang Ye, Ping Wang, Dongwei Ren, WangMeng Zuo, Qibin Hou, Ming-Ming Cheng
Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement.
no code implementations • 26 Jan 2021 • Wenliang Qian, Yang Xu, WangMeng Zuo, Hui Li
In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem.
no code implementations • 19 Jan 2021 • Wei Lian, WangMeng Zuo
The resulting lower bound problem has the merit that it can be efficiently solved via linear assignment and low dimensional convex quadratic programming.
1 code implementation • ICCV 2021 • Wei Shang, Dongwei Ren, Dongqing Zou, Jimmy S. Ren, Ping Luo, WangMeng Zuo
EFM can also be easily incorporated into existing deblurring networks, making event-driven deblurring task benefit from state-of-the-art deblurring methods.
1 code implementation • 2 Dec 2020 • Yu Li, Ming Liu, Yaling Yi, Qince Li, Dongwei Ren, WangMeng Zuo
To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.
1 code implementation • 10 Nov 2020 • Andrey Ignatov, Radu Timofte, Zhilu Zhang, Ming Liu, Haolin Wang, WangMeng Zuo, Jiawei Zhang, Ruimao Zhang, Zhanglin Peng, Sijie Ren, Linhui Dai, Xiaohong Liu, Chengqi Li, Jun Chen, Yuichi Ito, Bhavya Vasudeva, Puneesh Deora, Umapada Pal, Zhenyu Guo, Yu Zhu, Tian Liang, Chenghua Li, Cong Leng, Zhihong Pan, Baopu Li, Byung-Hoon Kim, Joonyoung Song, Jong Chul Ye, JaeHyun Baek, Magauiya Zhussip, Yeskendir Koishekenov, Hwechul Cho Ye, Xin Liu, Xueying Hu, Jun Jiang, Jinwei Gu, Kai Li, Pengliang Tan, Bingxin Hou
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
2 code implementations • 23 Oct 2020 • Yali Peng, Yue Cao, Shigang Liu, Jian Yang, WangMeng Zuo
To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance.
no code implementations • 25 Sep 2020 • Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, WangMeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding, Tangxin Xie, Liang Cao, Yan Zou, Yi Shen, Jialiang Zhang, Yu Jia, Kaihua Cheng, Chenhuan Wu, Yue Lin, Cen Liu, Yunbo Peng, Xueyi Zou, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Tongtong Zhao, Shanshan Zhao, Yoseob Han, Byung-Hoon Kim, JaeHyun Baek, HaoNing Wu, Dejia Xu, Bo Zhou, Wei Guan, Xiaobo Li, Chen Ye, Hao Li, Yukai Shi, Zhijing Yang, Xiaojun Yang, Haoyu Zhong, Xin Li, Xin Jin, Yaojun Wu, Yingxue Pang, Sen Liu, Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Wan-Chi Siu, Yuanbo Zhou, Rao Muhammad Umer, Christian Micheloni, Xiaofeng Cong, Rajat Gupta, Keon-Hee Ahn, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee, Feras Almasri, Thomas Vandamme, Olivier Debeir
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
1 code implementation • 21 Sep 2020 • Fei Xie, Wankou Yang, Bo Liu, Kaihua Zhang, Wanli Xue, WangMeng Zuo
Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations.
2 code implementations • ECCV 2020 • Xiaohe Wu, Ming Liu, Yue Cao, Dongwei Ren, WangMeng Zuo
As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set.
4 code implementations • 31 Aug 2020 • Kai Zhang, Yawei Li, WangMeng Zuo, Lei Zhang, Luc van Gool, Radu Timofte
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems.
1 code implementation • ECCV 2020 • Yuxiang Wei, Ming Liu, Haolin Wang, Ruifeng Zhu, Guosheng Hu, WangMeng Zuo
Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training.
1 code implementation • ECCV 2020 • Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, WangMeng Zuo, Liang Lin
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
1 code implementation • ECCV 2020 • Xiaoming Li, Chaofeng Chen, Shangchen Zhou, Xianhui Lin, WangMeng Zuo, Lei Zhang
Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block.
1 code implementation • 8 Jul 2020 • Chunwei Tian, Ruibin Zhuge, Zhihao Wu, Yong Xu, WangMeng Zuo, Chen Chen, Chia-Wen Lin
Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image.
Ranked #45 on Image Super-Resolution on Set14 - 4x upscaling
1 code implementation • 8 Jul 2020 • Chunwei Tian, Yong Xu, WangMeng Zuo, Bo Du, Chia-Wen Lin, David Zhang
The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network.
no code implementations • 5 Jul 2020 • Wei Lian, WangMeng Zuo, Lei Zhang
Our method is also $\epsilon-$globally optimal and thus is guaranteed to be robust.
1 code implementation • NeurIPS 2020 • Shangchen Zhou, Jiawei Zhang, WangMeng Zuo, Chen Change Loy
Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image.
1 code implementation • 24 Jun 2020 • Jiazhi Du, Xin Qiao, Zifei Yan, Hongzhi Zhang, WangMeng Zuo
For flexible non-blind image denoising, existing deep networks usually take both noisy image and noise level map as the input to handle various noise levels with a single model.
1 code implementation • 21 May 2020 • Jianrui Cai, WangMeng Zuo, and Lei Zhang
In this work, we propose a Dark and Bright Channel Priors embedded Network (DBCPeNet) to plug the channel priors into a neural network for effective dynamic scene deblurring.
Ranked #33 on Image Deblurring on GoPro (using extra training data)
no code implementations • 10 May 2020 • Mu Li, Kai Zhang, WangMeng Zuo, Radu Timofte, David Zhang
To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context.
1 code implementation • 8 May 2020 • Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte, Michael S. Brown, Yue Cao, Zhilu Zhang, WangMeng Zuo, Xiaoling Zhang, Jiye Liu, Wendong Chen, Changyuan Wen, Meng Liu, Shuailin Lv, Yunchao Zhang, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Xiyu Yu, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding, Songhyun Yu, Bumjun Park, Jechang Jeong, Shuai Liu, Ziyao Zong, Nan Nan, Chenghua Li, Zengli Yang, Long Bao, Shuangquan Wang, Dongwoon Bai, Jungwon Lee, Youngjung Kim, Kyeongha Rho, Changyeop Shin, Sungho Kim, Pengliang Tang, Yiyun Zhao, Yuqian Zhou, Yuchen Fan, Thomas Huang, Zhihao LI, Nisarg A. Shah, Wei Liu, Qiong Yan, Yuzhi Zhao, Marcin Możejko, Tomasz Latkowski, Lukasz Treszczotko, Michał Szafraniuk, Krzysztof Trojanowski, Yanhong Wu, Pablo Navarrete Michelini, Fengshuo Hu, Yunhua Lu, Sujin Kim, Wonjin Kim, Jaayeon Lee, Jang-Hwan Choi, Magauiya Zhussip, Azamat Khassenov, Jong Hyun Kim, Hwechul Cho, Priya Kansal, Sabari Nathan, Zhangyu Ye, Xiwen Lu, Yaqi Wu, Jiangxin Yang, Yanlong Cao, Siliang Tang, Yanpeng Cao, Matteo Maggioni, Ioannis Marras, Thomas Tanay, Gregory Slabaugh, Youliang Yan, Myungjoo Kang, Han-Soo Choi, Kyungmin Song, Shusong Xu, Xiaomu Lu, Tingniao Wang, Chunxia Lei, Bin Liu, Rajat Gupta, Vineet Kumar
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
6 code implementations • 7 May 2020 • Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, QinGhua Hu, WangMeng Zuo
In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.
1 code implementation • 8 Apr 2020 • Ming Liu, Zhilu Zhang, Liya Hou, WangMeng Zuo, Lei Zhang
Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints.
1 code implementation • CVPR 2020 • Qilong Wang, Li Zhang, Banggu Wu, Dongwei Ren, Peihua Li, WangMeng Zuo, QinGhua Hu
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.
3 code implementations • 12 Mar 2020 • Han Yang, Ruimao Zhang, Xiaobao Guo, Wei Liu, WangMeng Zuo, Ping Luo
First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on.
Ranked #4 on Virtual Try-on on VITON (IS metric)
1 code implementation • IEEE Transactions on Multimedia 2020 • Cairong Zhao, Xinbi Lv, Zhang Zhang, WangMeng Zuo, Jun Wu, Duoqian Miao
The extraction of robust feature representations from pedestrian images through CNNs with a single deterministic pooling operation is problematic as the features in real pedestrian images are complex and diverse.
no code implementations • 31 Dec 2019 • Chunwei Tian, Lunke Fei, Wenxian Zheng, Yong Xu, WangMeng Zuo, Chia-Wen Lin
However, there are substantial differences in the various types of deep learning methods dealing with image denoising.
12 code implementations • CVPR 2020 • Qilong Wang, Banggu Wu, Pengfei Zhu, Peihua Li, WangMeng Zuo, QinGhua Hu
By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity.
Ranked #734 on Image Classification on ImageNet
1 code implementation • ICCV 2019 • Zhaoyi Yan, Yuchen Yuan, WangMeng Zuo, Xiao Tan, Yezhen Wang, Shilei Wen, Errui Ding
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i. e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
2 code implementations • Neural Networks 2019 • Chunwei Tian, Yong Xu, WangMeng Zuo
In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet).
1 code implementation • ICCV 2019 • Chaohao Xie, Shaohui Liu, Chao Li, Ming-Ming Cheng, WangMeng Zuo, Xiao Liu, Shilei Wen, Errui Ding
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on Image Inpainting on Paris StreetView
2 code implementations • 26 Aug 2019 • Xin Li, Tianwei Lin, Xiao Liu, Chuang Gan, WangMeng Zuo, Chao Li, Xiang Long, Dongliang He, Fu Li, Shilei Wen
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
1 code implementation • CVPR 2020 • Dongwei Ren, Kai Zhang, Qilong Wang, QinGhua Hu, WangMeng Zuo
To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution.
3 code implementations • 6 Jul 2019 • Pengju Liu, Hongzhi Zhang, Wei Lian, WangMeng Zuo
Specifically, MWCNN for image restoration is based on U-Net architecture, and inverse wavelet transform (IWT) is deployed to reconstruct the high resolution (HR) feature maps.
2 code implementations • 24 Jun 2019 • Mu Li, Kede Ma, Jane You, David Zhang, WangMeng Zuo
For the former, we directly apply a CCN to the binarized representation of an image to compute the Bernoulli distribution of each code for entropy estimation.
1 code implementation • 2 Jun 2019 • Hao Wang, Qilong Wang, Fan Yang, Weiqi Zhang, WangMeng Zuo
For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance.
1 code implementation • 16 May 2019 • Feng Li, Xiaohe Wu, WangMeng Zuo, David Zhang, Lei Zhang
Therefore, we in this paper investigate the feasibility to remove cosine window from CF trackers with spatial regularization.
1 code implementation • ICCV 2019 • Shangchen Zhou, Jiawei Zhang, Jinshan Pan, Haozhe Xie, WangMeng Zuo, Jimmy Ren
To overcome the limitation of separate optical flow estimation, we propose a Spatio-Temporal Filter Adaptive Network (STFAN) for the alignment and deblurring in a unified framework.
Ranked #3 on Deblurring on DVD (using extra training data)
8 code implementations • CVPR 2019 • Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, WangMeng Zuo, Shilei Wen
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.
no code implementations • 19 Apr 2019 • Yiwen Guo, Ming Lu, WangMeng Zuo, Chang-Shui Zhang, Yurong Chen
Convolutional neural networks have been proven effective in a variety of image restoration tasks.
3 code implementations • 15 Apr 2019 • Qilong Wang, Jiangtao Xie, WangMeng Zuo, Lei Zhang, Peihua Li
The proposed methods are highly modular, readily plugged into existing deep CNNs.
Ranked #1 on Image Classification on iNaturalist (Top 3 Error metric)
1 code implementation • CVPR 2019 • Shangchen Zhou, Jiawei Zhang, WangMeng Zuo, Haozhe Xie, Jinshan Pan, Jimmy Ren
Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles.
3 code implementations • CVPR 2019 • Jinjin Gu, Hannan Lu, WangMeng Zuo, Chao Dong
In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown.
Ranked #2 on Blind Super-Resolution on Set5 - 3x upscaling
1 code implementation • 1 Apr 2019 • Mu Li, WangMeng Zuo, Shuhang Gu, Jane You, David Zhang
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance.
1 code implementation • CVPR 2019 • Kai Zhang, WangMeng Zuo, Lei Zhang
In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels.
1 code implementation • 25 Mar 2019 • Lei Zhang, Shan-Shan Wang, Guang-Bin Huang, WangMeng Zuo, Jian Yang, David Zhang
The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario.
no code implementations • 2 Mar 2019 • Jianrui Cai, WangMeng Zuo, Lei Zhang
In this work, we propose an Extreme Channel Prior embedded Network (ECPeNet) to plug the extreme channel priors (i. e., priors on dark and bright channels) into a network architecture for effective dynamic scene deblurring.
4 code implementations • CVPR 2019 • Dongwei Ren, WangMeng Zuo, QinGhua Hu, Pengfei Zhu, Deyu Meng
To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions.
Ranked #1 on Single Image Deraining on Rain1400
no code implementations • CVPR 2019 • Qi Xie, Minghao Zhou, Qian Zhao, Deyu Meng, WangMeng Zuo, Zongben Xu
In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image.
1 code implementation • 19 Dec 2018 • Xiaoming Li, Ming Liu, Jieru Zhu, WangMeng Zuo, Meng Wang, Guosheng Hu, Lei Zhang
As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.
Ranked #1 on Facial Inpainting on VggFace2
1 code implementation • NeurIPS 2018 • Qilong Wang, Zilin Gao, Jiangtao Xie, WangMeng Zuo, Peihua Li
However, both GAP and existing HOP methods assume unimodal distributions, which cannot fully capture statistics of convolutional activations, limiting representation ability of deep CNNs, especially for samples with complex contents.
no code implementations • NeurIPS 2018 • Wenqi Ren, Jiawei Zhang, Lin Ma, Jinshan Pan, Xiaochun Cao, WangMeng Zuo, Wei Liu, Ming-Hsuan Yang
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.
no code implementations • 7 Nov 2018 • Hongwei Yong, Deyu Meng, Jinxing Li, WangMeng Zuo, Lei Zhang
Different from single view case, MSL should take both common and specific knowledge among different views into consideration.
no code implementations • ECCV 2018 • Sijia Cai, WangMeng Zuo, Larry S. Davis, Lei Zhang
Video summarization is a challenging under-constrained problem because the underlying summary of a single video strongly depends on users' subjective understandings.
no code implementations • 17 Aug 2018 • Wenxue Cui, Tao Zhang, Shengping Zhang, Feng Jiang, WangMeng Zuo, Debin Zhao
To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.
no code implementations • 8 Aug 2018 • Mingrui Geng, Yun Deng, Qian Zhao, Qi Xie, Dong Zeng, WangMeng Zuo, Deyu Meng
To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training.
no code implementations • ECCV 2018 • Yingjie Yao, Xiaohe Wu, Lei Zhang, Shiguang Shan, WangMeng Zuo
In existing off-line deep learning models for CF trackers, the model adaptation usually is either abandoned or has closed-form solution to make it feasible to learn deep representation in an end-to-end manner.
3 code implementations • 26 Jul 2018 • Jun Xu, Mengyang Yu, Ling Shao, WangMeng Zuo, Deyu Meng, Lei Zhang, David Zhang
However, the negative entries in the coefficient matrix are forced to be positive when constructing the affinity matrix via exponentiation, absolute symmetrization, or squaring operations.
no code implementations • 23 Jul 2018 • Yajie Zhao, Weikai Chen, Jun Xing, Xiaoming Li, Zach Bessinger, Fuchang Liu, WangMeng Zuo, Ruigang Yang
Different from the state-of-the-art face inpainting methods that have no control over the synthesized content and can only handle frontal face pose, our approach can faithfully recover the missing content under various head poses while preserving the identity.
3 code implementations • CVPR 2019 • Shi Guo, Zifei Yan, Kai Zhang, WangMeng Zuo, Lei Zhang
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs.
Ranked #4 on Denoising on Darmstadt Noise Dataset
no code implementations • CVPR 2018 • Yunhan Shen, Rongrong Ji, Shengchuan Zhang, WangMeng Zuo, Yan Wang
Without the need of annotating bounding boxes, the existing methods usually follow a two/multi-stage pipeline with an online compulsive stage to extract object proposals, which is an order of magnitude slower than fast fully supervised object detectors such as SSD [31] and YOLO [34].
5 code implementations • 18 May 2018 • Pengju Liu, Hongzhi Zhang, Kai Zhang, Liang Lin, WangMeng Zuo
With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.
Ranked #2 on Grayscale Image Denoising on Set12 sigma25
no code implementations • ECCV 2018 • Lan Wang, Chenqiang Gao, Luyu Yang, Yue Zhao, WangMeng Zuo, Deyu Meng
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
1 code implementation • ECCV 2018 • Xiaoming Li, Ming Liu, Yuting Ye, WangMeng Zuo, Liang Lin, Ruigang Yang
For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet).
Ranked #1 on Image Super-Resolution on WebFace - 8x upscaling
no code implementations • CVPR 2018 • Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, WangMeng Zuo, Chunhua Shen, Rynson Lau, Ming-Hsuan Yang
To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.
1 code implementation • 12 Apr 2018 • Dongwei Ren, WangMeng Zuo, David Zhang, Lei Zhang, Ming-Hsuan Yang
For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well.
1 code implementation • 9 Apr 2018 • Gongning Luo, Suyu Dong, Kuanquan Wang, WangMeng Zuo, Shaodong Cao, Henggui Zhang
Methods: In this paper, we propose a direct volumes prediction method based on the end-to-end deep convolutional neural networks (CNN).
2 code implementations • CVPR 2018 • Hao Wang, Qilong Wang, Mingqi Gao, Peihua Li, WangMeng Zuo
Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation. Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection.
no code implementations • 26 Mar 2018 • Ibrahim Omara, Hongzhi Zhang, Faqiang Wang, WangMeng Zuo
Ear recognition task is known as predicting whether two ear images belong to the same person or not.
1 code implementation • CVPR 2018 • Feng Li, Cheng Tian, WangMeng Zuo, Lei Zhang, Ming-Hsuan Yang
Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5. 4% and 3. 6% AUC score on OTB-2015 and Temple-Color, respectively.
Ranked #9 on Visual Object Tracking on VOT2017/18