no code implementations • 11 May 2024 • Zeyu Xiao, Zhiwei Xiong
Recent advancements in light field super-resolution (SR) have yielded impressive results.
no code implementations • 5 May 2024 • Ziyun Qian, Zeyu Xiao, Zhenyi Wu, Dingkang Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Dongliang Kou, Lihua Zhang
To address these problems, we consider style motion as a condition and propose the Style Motion Conditioned Diffusion (SMCD) framework for the first time, which can more comprehensively learn the style features of motion.
no code implementations • 1 Feb 2024 • Ruisheng Gao, Yutong Liu, Zeyu Xiao, Zhiwei Xiong
Light fields (LFs), conducive to comprehensive scene radiance recorded across angular dimensions, find wide applications in 3D reconstruction, virtual reality, and computational photography. However, the LF acquisition is inevitably time-consuming and resource-intensive due to the mainstream acquisition strategy involving manual capture or laborious software synthesis. Given such a challenge, we introduce LFdiff, a straightforward yet effective diffusion-based generative framework tailored for LF synthesis, which adopts only a single RGB image as input. LFdiff leverages disparity estimated by a monocular depth estimation network and incorporates two distinctive components: a novel condition scheme and a noise estimation network tailored for LF data. Specifically, we design a position-aware warping condition scheme, enhancing inter-view geometry learning via a robust conditional signal. We then propose DistgUnet, a disentanglement-based noise estimation network, to harness comprehensive LF representations. Extensive experiments demonstrate that LFdiff excels in synthesizing visually pleasing and disparity-controllable light fields with enhanced generalization capability. Additionally, comprehensive results affirm the broad applicability of the generated LF data, spanning applications like LF super-resolution and refocusing.
1 code implementation • 28 Nov 2023 • Zhihe Lu, Jiawang Bai, Xin Li, Zeyu Xiao, Xinchao Wang
However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e. g., CLIP-ViT-B/16.
Ranked #2 on Prompt Engineering on ImageNet
1 code implementation • 30 May 2023 • Zeyu Xiao, Ruisheng Gao, Yutong Liu, Yueyi Zhang, Zhiwei Xiong
Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (e. g., bicubic downsampling) suffer from poor performance when applied to complex real-world scenarios.
no code implementations • 23 May 2023 • Zeyu Xiao, Jiawang Bai, Zhihe Lu, Zhiwei Xiong
This motivates the investigation and incorporation of prior knowledge in order to effectively constrain the solution space and enhance the quality of the restored images.
no code implementations • 11 May 2023 • Zhihe Lu, Zeyu Xiao, Jiawang Bai, Zhiwei Xiong, Xinchao Wang
To use the SAM-based prior, we propose a simple yet effective module -- SAM-guidEd refinEment Module (SEEM), which can enhance both alignment and fusion procedures by the utilization of semantic information.
1 code implementation • CVPR 2023 • Zeyu Xiao, Yutong Liu, Ruisheng Gao, Zhiwei Xiong
For the first time in light field SR, we propose a potent DA strategy called CutMIB to improve the performance of existing light field SR networks while keeping their structures unchanged.
2 code implementations • AAAI 2022 • Yurui Zhu, Zeyu Xiao, Yanchi Fang, Xueyang Fu, Zhiwei Xiong, Zheng-Jun Zha
To address these issues, we first propose a new shadow illumination model for the shadow removal task.
no code implementations • NeurIPS 2021 • Man Zhou, Zeyu Xiao, Xueyang Fu, Aiping Liu, Gang Yang, Zhiwei Xiong
Deep learning provides a new avenue for image restoration, which demands a delicate balance between fine-grained details and high-level contextualized information during recovering the latent clear image.
no code implementations • CVPR 2021 • Zeyu Xiao, Xueyang Fu, Jie Huang, Zhen Cheng, Zhiwei Xiong
In this paper, we aim to improve the performance of compact VSR networks without changing their original architectures, through a knowledge distillation approach that transfers knowledge from a complicated VSR network to a compact one.
1 code implementation • 11 May 2021 • Ruikang Xu, Zeyu Xiao, Jie Huang, Yueyi Zhang, Zhiwei Xiong
Image deblurring has seen a great improvement with the development of deep neural networks.