Documents
Poster
Long-distance Information Filtering Network for Compressed Video Quality Enhancement
![](https://sigport.org/sites/default/files/styles/home/public/DCC_2023_3_0.jpg?itok=Df5ZzK3h)
- Citation Author(s):
- Submitted by:
- Xuan Sun
- Last updated:
- 27 February 2023 - 6:59am
- Document Type:
- Poster
- Document Year:
- 2023
- Event:
- Presenters:
- Xuan Sun
- Paper Code:
- 167
- Categories:
- Log in to post comments
Restoring high-quality videos from low-quality compressed ones is a crucial research topic in video coding. Most existing methods do not exploit the information in the long-distance compressed frames. Even when they do, these methods ignore the effect of interference information during reconstruction. In this paper, we propose a unique Long-distance Information Filtering (LIF) scheme with the 3D-CNN, which enhances compressed videos by mining filtered and valid information from long-distance frames. Specifically, we propose a practical block, Long-distance Feature Extraction (LFE) block, to model the spatio-temporal relationship within a long temporal range. Furthermore, a progressive Information Filtering (IF) module is proposed in LFE to promote artifact removal and texture restoration by capturing a large effective receptive field, which can significantly boost the effect of LIF. Extensive experiments demonstrate that our method achieves state-of-the-art performance with nearly 25% of the parameters and half of the training volume, which indicates that our model is more lightweight and more efficient.