Yawei Li

Yawei Li

Auto-generated profile, based on publicly available information

Yawei Li

Integrated Systems Laboratory

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
JLJingyun Liang
Jingyun Liang
JCJiezhang Cao
Jiezhang Cao
YFYuchen Fan
Yuchen Fan
KZKai Zhang
Kai Zhang
RRRakesh Ranjan
Rakesh Ranjan
LGLuc Van Gool
Luc Van Gool
Video restoration aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which are restricted by frame-by-frame restoration. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction ability. More specifically, VRT is composed of multiple scales, each of which consists of two kinds of modules: temporal reciprocal self attention (TRSA) and parallel warping. TRSA divides the video into small clips, on which reciprocal attention is applied for joint motion estimation, feature alignment and feature fusion, while self attention is used for feature extraction. To enable cross-clip interactions, the video sequence is shifted for every other layer. Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping. Experimental results on five tasks, including video super-resolution, video deblurring, video denoising, video frame interpolation and space-time video super-resolution, demonstrate that VRT outperforms the state-of-the-art methods by large margins (up to 2.16dB) on fourteen benchmark datasets. The codes are available at https://github.com/JingyunLiang/VRT.

15 September 2023 in Machine Intelligence Research
Verified
Journal Article
Open access
PDF file
KZKai Zhang
Kai Zhang
YLYawei Li
Yawei Li
JLJingyun Liang
Jingyun Liang
JCJiezhang Cao
Jiezhang Cao
YZYulun Zhang
Yulun Zhang
LGLuc Van Gool
Luc Van Gool
While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research. The source code is available at https://github.com/cszn/SCUNet.

1 June 2020
Verified
Conference Paper
Closed access
YLYawei Li
Yawei Li
SGShuhang Gu
Shuhang Gu
CMChristoph Mayer
Christoph Mayer
LGLuc Van Gool
Luc Van Gool
Radu TimofteRadu Timofte
Radu Timofte
In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut connections (e.g. ResNet), filter pruning cannot deal with the last convolutional layer in a ResBlock while the low-rank decomposition methods can. In addition, we propose to compress the whole network jointly instead of in a layer-wise manner. Our approach proves its potential as it compares favorably to the state-of-the-art on several benchmarks. Code is available at https://github.com/ofsoundof/group_sparsity.

1 October 2019
Verified
Conference Paper
Closed access
SGShuhang Gu
Shuhang Gu
YLYawei Li
Yawei Li
LGLuc Van Gool
Luc Van Gool
Radu TimofteRadu Timofte
Radu Timofte

3 November 2022
Verified
Book Chapter
Closed access
PDF file
JCJiezhang Cao
Jiezhang Cao
JLJingyun Liang
Jingyun Liang
KZKai Zhang
Kai Zhang
YLYawei Li
Yawei Li
YZYulun Zhang
Yulun Zhang
LGLuc Van Gool
Luc Van Gool

7 November 2020
Verified
Book Chapter
Closed access
PDF file
YLYawei Li
Yawei Li
SGShuhang Gu
Shuhang Gu
KZKai Zhang
Kai Zhang
LGLuc Van Gool
Luc Van Gool
Radu TimofteRadu Timofte
Radu Timofte