# Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction

arXiv: https://arxiv.org/abs/2108.02110 · HTML: https://mlsanity.com/paper/2108.02110/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 4 Aug 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [A Comprehensive Study of Deep Video Action Recognition](https://mlsanity.com/paper/2012.06567/) (2020)
- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video](https://mlsanity.com/paper/1902.09707/) (2019)
- [Multi-Frame Quality Enhancement for Compressed Video](https://mlsanity.com/paper/1803.04680/) (2018)
- [Deep Generative Adversarial Compression Artifact Removal](https://mlsanity.com/paper/1704.02518/) (2017)
- [Enhancing Quality for HEVC Compressed Videos](https://mlsanity.com/paper/1709.06734/) (2017)
- [A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding](https://mlsanity.com/paper/1608.06690/) (2016)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)
- [Non-Local ConvLSTM for Video Compression Artifact Reduction](https://mlsanity.com/paper/1910.12286/) (2019)
- [One-to-Many Network for Visually Pleasing Compression Artifacts Reduction](https://mlsanity.com/paper/1611.04994/) (2016)
- [Image Restoration by Estimating Frequency Distribution of Local Patches](https://mlsanity.com/paper/1805.09097/) (2018)
- [Quality-Gated Convolutional LSTM for Enhancing Compressed Video](https://mlsanity.com/paper/1903.04596/) (2019)
- [DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images](https://mlsanity.com/paper/1805.10558/) (2018)
- [Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information](https://mlsanity.com/paper/2105.14962/) (2021)

## Built on by (most cited first, 14 of 14)

- [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022)
- [CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2403.10362/) (2024)
- [Learning Truncated Causal History Model for Video Restoration](https://mlsanity.com/paper/2410.03936/) (2024)
- [End-to-end Transformer for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2210.13827/) (2022)
- [Compressed Video Quality Enhancement with Temporal Group Alignment and Fusion](https://mlsanity.com/paper/2406.09693/) (2024)
- [Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement](https://mlsanity.com/paper/2202.00011/) (2022)
- [Grounding Degradations in Natural Language for All-In-One Video Restoration](https://mlsanity.com/paper/2507.14851/) (2025)
- [Online Video Quality Enhancement with Spatial-Temporal Look-up Tables](https://mlsanity.com/paper/2311.13616/) (2023)
- [Valid Information Guidance Network for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2303.00520/) (2023)
- [LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation](https://mlsanity.com/paper/2512.16313/) (2025)
- [GAN-Based Multi-View Video Coding with Spatio-Temporal EPI Reconstruction](https://mlsanity.com/paper/2205.03599/) (2022)
- [Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2403.11556/) (2024)
- [Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference](https://mlsanity.com/paper/2511.16137/) (2025)
- [MDFI: A Multi-Domain Features Integration for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2608.21495/) (2026)

## Abstract (arXiv)

A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of neighboring frames. However, these methods usually suffer from a narrow temporal scope, thus may miss some useful details from some frames outside the neighboring ones. In this paper, to boost artifact removal, on the one hand, we propose a Recursive Fusion (RF) module to model the temporal dependency within a long temporal range. Specifically, RF utilizes both the current reference frames and the preceding hidden state to conduct better spatiotemporal compensation. On the other hand, we design an efficient and effective Deformable Spatiotemporal Attention (DSTA) module such that the model can pay more effort on restoring the artifact-rich areas like the boundary area of a moving object. Extensive experiments show that our method outperforms the existing ones on the MFQE 2.0 dataset in terms of both fidelity and perceptual effect. Code is available at https://github.com/zhaominyiz/RFDA-PyTorch.