CVPR Findings2026
MVSSM: Motion-aware Visual State Space Model for Efficient Video Deblurring
Chen Zhou, Tao Wu, Wei Liu, Xi Wu, Ying Fu
Abstract
Video deblurring remains a challenging task due to the complex and spatially varying motion blur present in realworld scenes. Recent state space models (SSMs) have shown great promise in modeling long-range dependencies with linear complexity; however, their fixed scanning strategies often fail to capture motion-aware contextual information effectively. To address this limitation, we propose MVSSM, a Motion-aware Visual State Space Model that dynamically adapts its feature scanning direction based on estimated motion trajectories. Specifically, our Motion-aware Scanning Block (MSB) leverages optical flow to determine the dominant motion direction and selects an optimal scanning path-horizontal, vertical, or diagonal-to align feature propagation with actual motion patterns. Furthermore, we introduce a Multi-scale Dynamic Feature Fusion (MDFF) module that enhances spatiotemporal representation through pixel-wise dynamic convolutions across multiple scales. Experimental results on multiple synthetic and real-world datasets demonstrate that the proposed method not only substantially reduces computational burden but also achieves state-of-the-art performance in video deblurring. The code is available at MVSSM.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Restormer: Efficient Transformer for High-Resolution Image Restoration cites Uformer: A General U-Shaped Transformer for Image Restoration
- Recurrent Video Restoration Transformer with Guided Deformable Attention cites Uformer: A General U-Shaped Transformer for Image Restoration
- Recurrent Video Restoration Transformer with Guided Deformable Attention cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
Builds on21
- Restormer: Efficient Transformer for High-Resolution Image RestorationSyed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat et al.CVPR 2022 · 3,348 citations
- VMamba: Visual State Space ModelYue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu et al.NeurIPS 2024 · 3,199 citations
- Uformer: A General U-Shaped Transformer for Image RestorationZhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou et al.CVPR 2022 · 1,970 citations
- BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and AlignmentKelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change LoyCVPR 2022 · 522 citations
- Recurrent Video Restoration Transformer with Guided Deformable AttentionJingyun Liang, Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan et al.NeurIPS 2022 · 318 citations
Related papers
- Efficient Visual State Space Model for Image DeblurringLingshun Kong, Jiangxin Dong, Jinhui Tang, Ming-Hsuan Yang et al.CVPR 2025
- CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic ScanningYubin Gu, Boyang Hou, Yuan Meng, Wenting Luo et al.CVPR 2026
- Trajectory-aware Shifted State Space Models for Online Video Super-ResolutionQiang Zhu, Xiandong Meng, Yuxuan Jiang, Fan Zhang et al.ICLR 2026 · 3 citations
- Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State FusionChaodong Xiao, Minghan Li, Zhengqiang Zhang, Deyu Meng et al.ICLR 2025
- VSSD: Vision Mamba With Non-Causal State Space DualityYuheng Shi, Mingjia Li, Minjing Dong, Chang XuICCV 2025 · 20 citations
