English

Compressed Video Super-Resolution based on Hierarchical Encoding

Image and Video Processing 2025-06-18 v1 Computer Vision and Pattern Recognition

Abstract

This paper presents a general-purpose video super-resolution (VSR) method, dubbed VSR-HE, specifically designed to enhance the perceptual quality of compressed content. Targeting scenarios characterized by heavy compression, the method upscales low-resolution videos by a ratio of four, from 180p to 720p or from 270p to 1080p. VSR-HE adopts hierarchical encoding transformer blocks and has been sophisticatedly optimized to eliminate a wide range of compression artifacts commonly introduced by H.265/HEVC encoding across various quantization parameter (QP) levels. To ensure robustness and generalization, the model is trained and evaluated under diverse compression settings, allowing it to effectively restore fine-grained details and preserve visual fidelity. The proposed VSR-HE has been officially submitted to the ICME 2025 Grand Challenge on VSR for Video Conferencing (Team BVI-VSR), under both the Track 1 (General-Purpose Real-World Video Content) and Track 2 (Talking Head Videos).

Keywords

Cite

@article{arxiv.2506.14381,
  title  = {Compressed Video Super-Resolution based on Hierarchical Encoding},
  author = {Yuxuan Jiang and Siyue Teng and Qiang Zhu and Chen Feng and Chengxi Zeng and Fan Zhang and Shuyuan Zhu and Bing Zeng and David Bull},
  journal= {arXiv preprint arXiv:2506.14381},
  year   = {2025}
}
R2 v1 2026-07-01T03:21:37.173Z