Compressed Video Super-Resolution based on Hierarchical Encoding

TL;DR

This paper introduces VSR-HE, a hierarchical transformer-based method for enhancing the perceptual quality of heavily compressed videos, effectively restoring details and reducing artifacts across various compression levels.

Contribution

The paper proposes a novel hierarchical encoding transformer architecture tailored for compressed video super-resolution, optimized to handle artifacts from H.265/HEVC encoding.

Findings

Effective artifact removal across multiple QP levels

Restores fine details in heavily compressed videos

Achieves high perceptual quality in super-resolution

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).