# Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring

arXiv: https://arxiv.org/abs/2406.07551 · HTML: https://mlsanity.com/paper/2406.07551/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Spatio-Temporal Filter Adaptive Network for Video Deblurring](https://mlsanity.com/paper/1904.12257/) (2019)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring](https://mlsanity.com/paper/2103.04260/) (2021)
- [Online Video Deblurring via Dynamic Temporal Blending Network](https://mlsanity.com/paper/1704.03285/) (2017)
- [Flow-Guided Sparse Transformer for Video Deblurring](https://mlsanity.com/paper/2201.01893/) (2022)
- [Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes](https://mlsanity.com/paper/2108.09982/) (2021)
- [Learning Blind Motion Deblurring](https://mlsanity.com/paper/1708.04208/) (2017)
- [Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network](https://mlsanity.com/paper/2106.16028/) (2021)
- [Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring](https://mlsanity.com/paper/2112.05150/) (2021)
- [Spatio-Temporal Deformable Attention Network for Video Deblurring](https://mlsanity.com/paper/2207.10852/) (2022)
- [Multi-Scale Memory-Based Video Deblurring](https://mlsanity.com/paper/2204.02977/) (2022)

## Built on by (most cited first, 17 of 17)

- [Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video](https://mlsanity.com/paper/2412.06424/) (2024)
- [Motion-Aware Animatable Gaussian Avatars Deblurring](https://mlsanity.com/paper/2411.16758/) (2024)
- [Event-Enhanced Blurry Video Super-Resolution](https://mlsanity.com/paper/2504.13042/) (2025)
- [EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing](https://mlsanity.com/paper/2602.15031/) (2026)
- [UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance](https://mlsanity.com/paper/2504.09069/) (2025)
- [Coding-Prior Guided Diffusion Network for Video Deblurring](https://mlsanity.com/paper/2504.12222/) (2025)
- [Joint Flow And Feature Refinement Using Attention For Video Restoration](https://mlsanity.com/paper/2505.16434/) (2025)
- [NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather](https://mlsanity.com/paper/2603.27228/) (2026)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)
- [Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos](https://mlsanity.com/paper/2510.10691/) (2025)
- [CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image](https://mlsanity.com/paper/2501.14264/) (2025)
- [Adaptive Identification of Blurred Regions for Accurate Image Deblurring](https://mlsanity.com/paper/2502.20880/) (2025)
- [X-DECODE: EXtreme Deblurring with Curriculum Optimization and Domain Equalization](https://mlsanity.com/paper/2504.08072/) (2025)
- [SelfHVD: Self-Supervised Handheld Video Deblurring](https://mlsanity.com/paper/2508.08605/) (2025)
- [FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring](https://mlsanity.com/paper/2512.04390/) (2025)
- [RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring](https://mlsanity.com/paper/2607.20628/) (2026)
- [Binarized High-Efficiency RAW Video Restoration and Beyond](https://mlsanity.com/paper/2608.16756/) (2026)

## Abstract (arXiv)

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, leveraging 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 outperforms the state-of-the-art methods on the GoPro and DVD datasets.