News
2022-06-10: Our new paper RVRT achieves SOTA video restoration results with balanced size, memory and runtime.
2022-04-01: Our new paper SCUNet achieves awesome denoising performance for real-world images.
2022-01-28: Our new paper VRT outperforms previous video SR/ deblurring/ denoising/ frame interpolation/ space-time video SR methods by up to 2.16dB!
2021-10-20: SwinIR is awarded the best paper prize in ICCV-AIM2021.
2021-08-01: Three papers (HCFlow , MANet and BSRGAN ) accepted by ICCV2021.
2021-03-29: One paper (FKP ) accepted by CVPR2021.
Your browser does not support the video tag.
Recurrent Video Restoration Transformer with Guided Deformable Attention
Jingyun Liang , Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan, Eddy Ilg, Simon Green, Jiezhang Cao, Kai Zhang, Radu Timofte, Luc Van Gool
arxiv , 2022
arXiv /
code /
bibtex
A transformer-based model that jointly extracts, aligns, and fuses frame features at multiple scales; state-of-the-art performance in video SR/ deblurring/ denoising.
Your browser does not support the video tag.
Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis
Kai Zhang, Yawei Li, Jingyun Liang , Jiezhang Cao, Yulun Zhang, Hao Tang, Radu Timofte and Luc Van Gool
arxiv , 2022
arXiv /
code /
bibtex
A practical real-world image denoising model with impressive results on real-world images.
Your browser does not support the video tag.
VRT: A Video Restoration Transformer
Jingyun Liang , Jiezhang Cao, Yuchen Fan, Kai Zhang, Rakesh Ranjan, Yawei Li, Radu Timofte and Luc Van Gool
arxiv , 2022
arXiv /
code /
bibtex
A transformer-based model that jointly extracts, aligns, and fuses frame features at multiple scales; state-of-the-art performance in video SR/ deblurring/ denoising/ frame interpolation/ space-time video SR.
Your browser does not support the video tag.
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
Lei Sun, Christos Sakaridis, Jingyun Liang , Qi Jiang, Kailun Yang, Peng Sun, Yaozu Ye, Kaiwei Wang and Luc Van Gool
arxiv , 2021
arXiv /
code (coming soon) /
dataset (coming soon) /
bibtex
An unfolded end-to-end event camera-based motion deblurring method; a High-Quality Blur (HQBlur) dataset for event camera-based deblurring.
Your browser does not support the video tag.
SwinIR: Image Restoration Using Swin Transformer
Jingyun Liang , Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool and Radu Timofte
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW ) , 2021
arXiv /
code /
online demo /
bibtex
A transformer-based image restoration that allows content-based interactions and long-range dependency modelling; state-of-the-art performance on image SR, denoising and JPEG compression artifact reduction.
Your browser does not support the video tag.
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Kai Zhang, Jingyun Liang , Luc Van Gool and Radu Timofte
IEEE/CVF International Conference on Computer Vision (ICCV ) , 2021
arXiv /
code /
online demo /
bibtex
The first practical real-world degradation model for training real-world image SR models; impressive results on real-world images.
Your browser does not support the video tag.
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Jingyun Liang , Andreas Lugmayr, Kai Zhang, Martin Danelljan, Luc Van Gool and Radu Timofte
IEEE/CVF International Conference on Computer Vision (ICCV ) , 2021
arXiv /
code /
online demo /
bibtex
It learns a bijective mapping between HR and LR image pairs by modelling low and high-frequency components; a unified framework for image SR and image rescaling.
Your browser does not support the video tag.
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Jingyun Liang , Guolei Sun, Kai Zhang, Luc Van Gool and Radu Timofte
IEEE/CVF International Conference on Computer Vision (ICCV ) , 2021
arXiv /
code /
online demo /
bibtex
A kernel estimation network with mutual affine convolution for spatially variant kernels; state-of-the-art blind SR performance.
Your browser does not support the video tag.
Flow-based Kernel Prior with Application to Blind Super-Resolution
Jingyun Liang , Kai Zhang, Shuhang Gu, Luc Van Gool, Radu Timofte
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ) , 2021
arXiv /
code /
bibtex
A normalizing flow-based kernel prior for kernel modeling; state-of-the-art performance in unsupervised blind SR.