Hugging Face Trending Papers

Overview of Cross-Component In-loop Filters in Video Coding Standards

Read the original on Hugging Face Trending Papers →

In-loop filters have been comprehensively explored during the development of video coding standards due to their remarkable noise-reduction capability. In the early stage of video coding, in-loop filters, such as Deblocking Filter, Sample Adaptive Offset, and Adaptive Loop Filter, were performed separately for each component.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Computer Vision
Sep 22

Optimized Adaptive Loop Filter in Versatile Video Coding

arXiv:2607.05737v3 Announce Type: replace Abstract: In the Versatile Video Coding~(VVC) standard, adaptive loop filter~(ALF), including Geometry transformation-based Adaptive Loop Filter~(GALF) and C...

By Xuewei Meng, Jiaqi Zhang, Chuanmin Jia, Xinfeng Zhang, Shanshe Wang, Siwei Ma
arXiv Computer Vision
Sep 17

Flexible-Region Based Adaptive In-Loop Filter for Video Coding

The paper proposes a Flexible-Region Based Adaptive In-Loop Filter (FRALF) for video coding, extending the existing Adaptive Loop Filter (ALF) used in AVS3 by introducing multiple region partition templates such as 2×4, 4×4, 4×8, and 8×8. It also presents a filter coefficient merging algorithm that estimates distortion levels across different partition regions to further improve coding efficiency. Experimental results demonstrate that FRALF outperforms the current region-based ALF in AVS3 while keeping complexity increases relatively low.

By Xuewei Meng, Chuanmin Jia, Jing Cui, Shanshe Wang, Siwei Ma
Hugging Face Trending Papers
Jul 8

DiffCVE: Diffusion-based Compressed Video Enhancement

Perceptual quality enhancement of severely compressed videos remains challenging due to complex artifact patterns and substantial information loss. Recent diffusion models have demonstrated strong generative capability for visual restoration, but directly applying them to compressed video often ignores compression degradation characteristics and may introduce structure-inconsistent hallucinations.