# FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring

arXiv: https://arxiv.org/abs/2401.03707 · HTML: https://mlsanity.com/paper/2401.03707/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 87 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [TDAN: Temporally Deformable Alignment Network for Video Super-Resolution](https://mlsanity.com/paper/1812.02898/) (2018)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Video Frame Interpolation via Adaptive Separable Convolution](https://mlsanity.com/paper/1708.01692/) (2017)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (2018)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)

## Built on by (most cited first, 28 of 28)

- [SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration](https://mlsanity.com/paper/2501.01320/) (2025)
- [SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training](https://mlsanity.com/paper/2506.05301/) (2025)
- [DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models](https://mlsanity.com/paper/2407.01519/) (2024)
- [Solving Video Inverse Problems Using Image Diffusion Models](https://mlsanity.com/paper/2409.02574/) (2024)
- [Restereo: Diffusion stereo video generation and restoration](https://mlsanity.com/paper/2506.06023/) (2025)
- [Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion](https://mlsanity.com/paper/2512.23709/) (2025)
- [Event-Enhanced Blurry Video Super-Resolution](https://mlsanity.com/paper/2504.13042/) (2025)
- [SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution](https://mlsanity.com/paper/2506.19838/) (2025)
- [Blind Video Super-Resolution based on Implicit Kernels](https://mlsanity.com/paper/2503.07856/) (2025)
- [DiTVR: Zero-Shot Diffusion Transformer for Video Restoration](https://mlsanity.com/paper/2508.07811/) (2025)
- [DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution](https://mlsanity.com/paper/2603.22271/) (2026)
- [Rethinking Video Super-Resolution: Towards Diffusion-Based Methods without Motion Alignment](https://mlsanity.com/paper/2503.03355/) (2025)
- [DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior](https://mlsanity.com/paper/2502.03502/) (2025)
- [Joint Flow And Feature Refinement Using Attention For Video Restoration](https://mlsanity.com/paper/2505.16434/) (2025)
- [Seeing the Unseen: Zooming in the Dark with Event Cameras](https://mlsanity.com/paper/2601.02206/) (2026)
- [NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather](https://mlsanity.com/paper/2603.27228/) (2026)
- [DaBiT: Depth and Blur informed Transformer for Video Focal Deblurring](https://mlsanity.com/paper/2407.01230/) (2024)
- [MoCHA-former: Moir'e-Conditioned Hybrid Adaptive Transformer for Video Demoir'eing](https://mlsanity.com/paper/2508.14423/) (2025)
- [See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops](https://mlsanity.com/paper/2508.17932/) (2025)
- [HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution](https://mlsanity.com/paper/2601.04682/) (2026)
- [DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis](https://mlsanity.com/paper/2602.23022/) (2026)
- [AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark](https://mlsanity.com/paper/2607.02131/) (2026)
- [Optimization of Module Transferability in Single Image Super-Resolution: Universality Assessment and Cycle Residual Blocks](https://mlsanity.com/paper/2505.03522/) (2025)
- [FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring](https://mlsanity.com/paper/2512.04390/) (2025)
- [Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models](https://mlsanity.com/paper/2601.21922/) (2026)
- [UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration](https://mlsanity.com/paper/2604.00381/) (2026)
- [Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction](https://mlsanity.com/paper/2605.26230/) (2026)
- [DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution](https://mlsanity.com/paper/2605.30431/) (2026)

## Abstract (arXiv)

We present a joint learning scheme of video super-resolution and deblurring, called VSRDB, to restore clean high-resolution (HR) videos from blurry low-resolution (LR) ones. This joint restoration problem has drawn much less attention compared to single restoration problems. In this paper, we propose a novel flow-guided dynamic filtering (FGDF) and iterative feature refinement with multi-attention (FRMA), which constitutes our VSRDB framework, denoted as FMA-Net. Specifically, our proposed FGDF enables precise estimation of both spatio-temporally-variant degradation and restoration kernels that are aware of motion trajectories through sophisticated motion representation learning. Compared to conventional dynamic filtering, the FGDF enables the FMA-Net to effectively handle large motions into the VSRDB. Additionally, the stacked FRMA blocks trained with our novel temporal anchor (TA) loss, which temporally anchors and sharpens features, refine features in a course-to-fine manner through iterative updates. Extensive experiments demonstrate the superiority of the proposed FMA-Net over state-of-the-art methods in terms of both quantitative and qualitative quality. Codes and pre-trained models are available at: https://kaist-viclab.github.io/fmanet-site