Compressed Video Super-Resolution based on Hierarchical Encoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Yuxuan, Teng, Siyue, Zhu, Qiang, Feng, Chen, Zeng, Chengxi, Zhang, Fan, Zhu, Shuyuan, Zeng, Bing, Bull, David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912436037091328
author Jiang, Yuxuan
Teng, Siyue
Zhu, Qiang
Feng, Chen
Zeng, Chengxi
Zhang, Fan
Zhu, Shuyuan
Zeng, Bing
Bull, David
author_facet Jiang, Yuxuan
Teng, Siyue
Zhu, Qiang
Feng, Chen
Zeng, Chengxi
Zhang, Fan
Zhu, Shuyuan
Zeng, Bing
Bull, David
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2506_14381
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compressed Video Super-Resolution based on Hierarchical Encoding
Jiang, Yuxuan
Teng, Siyue
Zhu, Qiang
Feng, Chen
Zeng, Chengxi
Zhang, Fan
Zhu, Shuyuan
Zeng, Bing
Bull, David
Image and Video Processing
Computer Vision and Pattern Recognition
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).
title Compressed Video Super-Resolution based on Hierarchical Encoding
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14381