Blur-Aware Spatio-Temporal Sparse Transformer for Video Deblurring
Huicong Zhang, Haozhe Xie, Hongxun Yao
Abstract
Video deblurring relies on leveraging information from other frames in the video sequence to restore the blurred regions in the current frame. Mainstream approaches employ bidirectional feature propagation, spatio-temporal Transformers, or a combination of both to extract information from the video sequence. However, limitations in memory and computational resources constraints the temporal window length of the spatio-temporal transformer, preventing the extraction of longer temporal contextual information from the video sequence. Additionally, bidirectional feature propagation is highly sensitive to inaccurate optical flow in blurry frames, leading to error accumulation during the propagation process. To address these issues, we propose BSSTNet, Blur-aware Spatio-temporal Sparse Transformer Network. It introduces the blur map, which converts the originally dense attention into a sparse form, enabling a more extensive utilization of information throughout the entire video sequence. Specifically, BSSTNet (1) uses a longer temporal window in the transformer, lever-aging information from more distant frames to restore the blurry pixels in the current frame. (2) introduces bidirectional feature propagation guided by blur maps, which reduces error accumulation caused by the blur frame. The experimental results demonstrate the proposed BSSTNet out-performs the state-of-the-art methods on the GoPro and DVD datasets.
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.
18 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- EVDM: Event-based Real-World Video Deblurring with Mamba cites Recurrent Video Restoration Transformer with Guided Deformable Attention
- EVDM: Event-based Real-World Video Deblurring with Mamba cites Motion-adaptive Transformer for Event-based Image Deblurring
- ProPainter: Improving Propagation and Transformer for Video Inpainting cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- ProPainter: Improving Propagation and Transformer for Video Inpainting cites Spatio-Temporal Filter Adaptive Network for Video Deblurring
- ProPainter: Improving Propagation and Transformer for Video Inpainting cites FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
- Recurrent Video Restoration Transformer with Guided Deformable Attention cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- Recurrent Video Restoration Transformer with Guided Deformable Attention cites Spatio-Temporal Filter Adaptive Network for Video Deblurring
- EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing cites ProPainter: Improving Propagation and Transformer for Video Inpainting
- EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing cites FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
- BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment cites Spatio-Temporal Filter Adaptive Network for Video Deblurring
- Event-Enhanced Blurry Video Super-Resolution cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
Cited by top-tier papers18
- Motion-adaptive Transformer for Event-based Image DeblurringSenyan Xu, Zhijing Sun, Mingchen Zhong, Chengzhi Cao et al.AAAI 2025 · 17 citations
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion DeblurringWen Yang, Jinjian Wu, Leida Li, Weisheng Dong et al.AAAI 2025 · 7 citations
- Event-Enhanced Blurry Video Super-ResolutionDachun Kai, Yueyi Zhang, Jin Wang, Zeyu Xiao et al.AAAI 2025 · 7 citations
- EVDM: Event-based Real-World Video Deblurring with MambaZhijing Sun, Senyan Xu, Kean Liu, Runze Tian et al.ICCV 2025 · 6 citations
- EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video EditingYehonathan Litman, Shikun Liu, Dario Seyb, Nicholas Milef et al.CVPR 2026 · 5 citations
Builds on9
- 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
- Spatio-Temporal Filter Adaptive Network for Video DeblurringShangchen Zhou, Jiawei Zhang, Jinshan Pan, Wangmeng Zuo et al.ICCV 2019 · 225 citations
- ProPainter: Improving Propagation and Transformer for Video InpaintingShangchen Zhou, Chongyi Li, Kelvin C. K. Chan, Chen Change LoyICCV 2023 · 205 citations
- FuseFormer: Fusing Fine-Grained Information in Transformers for Video InpaintingRui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi et al.ICCV 2021 · 165 citations
Related papers
- Flow-Guided Sparse Transformer for Video DeblurringJing Lin, Yuanhao Cai, Xiaowan Hu, Haoqian Wang et al.ICML 2022 · 82 citations
- Video Frame Interpolation TransformerZhihao Shi, Xiangyu Xu, Xiaohong Liu, Jun Chen et al.CVPR 2022 · 117 citations
- Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video DenoisingZikang Chen, Tao Jiang, Xiaowan Hu, Wang Zhang et al.AAAI 2025 · 3 citations
- Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image DenoisingJunyi Li, Zhilu Zhang, Wangmeng ZuoAAAI 2025 · 31 citations
- SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationBrendan Duke, Abdalla Ahmed, Christian Wolf, Parham Aarabi et al.CVPR 2021
