We work on developing novel and practical techniques to address a range of image and video restoration problems, including image super-resolution, denoising, video super-resolution, details enhancement, video deblurring, frame interpolation, low-light image enhancement, and also lately for NeRF-synthesized view enhancement.
Single-Image Super-Resolution (SR), Image Denoising, JPEG Image Deblocking, Depth Map SR, Reference-Based SR:
K. Zhou, X. Lin, and J. Lu, “TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Nashville, TN, Jun. 2025. (PDF)
K. Zhou, X. Lin, Z. Liu, X. Han, and J. Lu, “UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond,” Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec. 2024. (PDF)
W. Li, K. Zhou, L. Qi, L. Lu, and J. Lu, “Best-Buddy GANs for Highly Detailed Image Super-Resolution,” AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, Feb. 2022. (Oral presentation) (PDF) (Slides)
L. Lu, W. Li, X. Tao, J. Lu, and J. Jia, “MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-resolution,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Nashville, TN, Jun. 2021. (PDF)
W. Li, K. Zhou, L. Qi, N. Jiang, J. Lu, and J. Jia, “LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond,” Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec. 2020. (PDF) (Supplementary) (Code)
NeRF-Synthesized View Enhancement, Improved NeRF in Non-static Scenes:
J. Chen, Y. Qin, L. Liu, J. Lu, and G. Li, “NeRF-HuGS: Improved NeRF in Non-static Scenes Using Heuristics-Guided Segmentation,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Seattle, WA, Jun. 2024. (Oral & also Best Paper Award candidate, top 0.2% of 11, 532 paper submissions) (Project page)
K. Zhou, W. Li, N.-J. Jiang, X. Han, and J. Lu, “From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm,” IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), to appear 2023. (preprint) (Project page)
K. Zhou, W. Li, Y. Wang, T. Hu, N. Jiang, X. Han, and J. Lu, “NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 2023. (PDF) (Project page)
Video Super-Resolution, Video Restoration (VSR, Denoising, Deblurring), Video Frame Interpolation:
X. Xu, Y. Yu, N. Jiang, J. Wu, B. Yu, J. Lu, and J. Jia, “PVDD: A Practical Benchmark Dataset and Network for Video Denoising,” Frontiers of Computer Science, Nov. 2025. (Link)
K. Zhou, W. Li, L. Lu, X. Han, and J. Lu, “Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 2023. (PDF)
K. Zhou, W. Li, L. Lu, X. Han, and J. Lu, “Revisiting Temporal Alignment for Video Restoration,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, Jun. 2022. (PDF)
L. Lu, R. Wu, H. Lin, J. Lu, and J. Jia, “Video Frame Interpolation with Transformer,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, Jun. 2022. (PDF)
W. Li, X. Tao, T. Guo, L. Qi, J. Lu, and J. Jia, “MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution,” European Conf. Computer Vision (ECCV), Glasgow, UK, Aug. 2020. (PDF) (Code)
Pre-training for Low-Level Vision (e.g. SR, Denoising, Deraining), Image Denoising:
W. Li, X. Lu, S. Qian, and J. Lu, “On Efficient Transformer-Based Image Pre-training for Low-Level Vision,” in Proc. International Joint Conference on Artificial Intelligence (IJCAI) , Macao, S. A. R., Aug. 2023. (PDF)
H. Liu, L. Li, J. Lu, and S. Tan, “Group Sparsity Mixture Model and Its Application on Image Denoising,” IEEE Trans. on Image Processing (TIP), vol. 31, pp. 5677-5690, 2022. (link)
H. Liu, X. Liu, J. Lu, and S. Tan, “Self-Supervised Image Prior Learning with GMM from a Single Noisy Image,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), Oct. 2021. (Oral presentation, A.R.= 3.4%) (PDF) (Slides)
Low-Light Image Enhancement:
K. Zhou, X. Lin, W. Li, X. Xu, Y. Cai, Z. Liu, X. Han, and J. Lu, “Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement ,” European Conf. Computer Vision (ECCV), Milano, Italy, Oct. 2024. (Project page) (PDF)
X. Xu, R. Wang, and J. Lu, “Low-Light Image Enhancement via Structure Modeling and Guidance,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 2023. (PDF)
R. Wang, X. Xu, C.-W. Fu, J. Lu, B. Yu, and J. Jia, “Seeing Dynamic Scenes in the Dark: A High-Quality Video Dataset with Mechatronic Alignment,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), Oct. 2021. (PDF) (Project page)
High-Performance Accelerators for Super-Resolution:
H. Liu, Y. Qian, Y. Liang, B. Zhang, Z. Liu, T. He, W. Zhao, J. Lu, and B. Yu, “A High-Performance Accelerator for Real-Time Super-Resolution on Edge FPGAs,” ACM Trans. on Design Automation of Electronic Systems (TODAES), 2024. (preprint)
W. Zhao, Y. Bai, Q. Sun, W. Li, H. Zheng, N. Jiang, J. Lu, B. Yu, and M. D.-F. Wong, “A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU,” IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023. (link)