# Quality-Gated Convolutional LSTM for Enhancing Compressed Video

arXiv: https://arxiv.org/abs/1903.04596 · HTML: https://mlsanity.com/paper/1903.04596/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

## Built on by (most cited first, 11 of 11)

- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)
- [NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results](https://mlsanity.com/paper/2204.09314/) (2022)
- [AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results](https://mlsanity.com/paper/2208.11184/) (2022)
- [Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction](https://mlsanity.com/paper/2108.02110/) (2021)
- [NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results](https://mlsanity.com/paper/2505.03007/) (2025)
- [Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration](https://mlsanity.com/paper/2205.10195/) (2022)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study](https://mlsanity.com/paper/2104.10782/) (2021)
- [Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information](https://mlsanity.com/paper/2105.14962/) (2021)
- [Multi-frame Joint Enhancement for Early Interlaced Videos](https://mlsanity.com/paper/2109.14151/) (2021)
- [Leveraging Video Coding Knowledge for Deep Video Enhancement](https://mlsanity.com/paper/2302.13594/) (2023)
- [Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis](https://mlsanity.com/paper/2607.16319/) (2026)

## Abstract (arXiv)

The past decade has witnessed great success in applying deep learning to enhance the quality of compressed video. However, the existing approaches aim at quality enhancement on a single frame, or only using fixed neighboring frames. Thus they fail to take full advantage of the inter-frame correlation in the video. This paper proposes the Quality-Gated Convolutional Long Short-Term Memory (QG-ConvLSTM) network with bi-directional recurrent structure to fully exploit the advantageous information in a large range of frames. More importantly, due to the obvious quality fluctuation among compressed frames, higher quality frames can provide more useful information for other frames to enhance quality. Therefore, we propose learning the "forget" and "input" gates in the ConvLSTM cell from quality-related features. As such, the frames with various quality contribute to the memory in ConvLSTM with different importance, making the information of each frame reasonably and adequately used. Finally, the experiments validate the effectiveness of our QG-ConvLSTM approach in advancing the state-of-the-art quality enhancement of compressed video, and the ablation study shows that our QG-ConvLSTM approach is learnt to make a trade-off between quality and correlation when leveraging multi-frame information. The project page: https://github.com/ryangchn/QG-ConvLSTM.git.