Saved in:
Bibliographic Details
Main Authors: Pang, Yingxue, Zhao, Shijie, Guo, Mengxi, Li, Junlin, Zhang, Li
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.08794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911102443454464
author Pang, Yingxue
Zhao, Shijie
Guo, Mengxi
Li, Junlin
Zhang, Li
author_facet Pang, Yingxue
Zhao, Shijie
Guo, Mengxi
Li, Junlin
Zhang, Li
contents Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Region-Adaptive Video Sharpening via Rate-Perception Optimization
Pang, Yingxue
Zhao, Shijie
Guo, Mengxi
Li, Junlin
Zhang, Li
Computer Vision and Pattern Recognition
Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.
title Region-Adaptive Video Sharpening via Rate-Perception Optimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08794