Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ding, Ding, Li, Daowen, Chen, Ying, Gao, Yixin, Dong, Ruixiao, Li, Kai, Li, Li
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.06655
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914456134483968
author Ding, Ding
Li, Daowen
Chen, Ying
Gao, Yixin
Dong, Ruixiao
Li, Kai
Li, Li
author_facet Ding, Ding
Li, Daowen
Chen, Ying
Gao, Yixin
Dong, Ruixiao
Li, Kai
Li, Li
contents Perceptual video compression adopts generative video modeling to improve perceptual realism but frequently sacrifices signal fidelity, diverging from the goal of video compression to faithfully reproduce visual signal. To alleviate the dilemma between perception and fidelity, in this paper we propose Controllable Generative Video Compression (CGVC) paradigm to faithfully generate details guided by multiple visual conditions. Under the paradigm, representative keyframes of the scene are coded and used to provide structural priors for non-keyframe generation. Dense per-frame control prior is additionally coded to better preserve finer structure and semantics of each non-keyframe. Guided by these priors, non-keyframes are reconstructed by controllable video generation model with temporal and content consistency. Furthermore, to accurately recover color information of the video, we develop a color-distance-guided keyframe selection algorithm to adaptively choose keyframes. Experimental results show CGVC outperforms previous perceptual video compression method in terms of both signal fidelity and perceptual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06655
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Controllable Generative Video Compression
Ding, Ding
Li, Daowen
Chen, Ying
Gao, Yixin
Dong, Ruixiao
Li, Kai
Li, Li
Computer Vision and Pattern Recognition
Perceptual video compression adopts generative video modeling to improve perceptual realism but frequently sacrifices signal fidelity, diverging from the goal of video compression to faithfully reproduce visual signal. To alleviate the dilemma between perception and fidelity, in this paper we propose Controllable Generative Video Compression (CGVC) paradigm to faithfully generate details guided by multiple visual conditions. Under the paradigm, representative keyframes of the scene are coded and used to provide structural priors for non-keyframe generation. Dense per-frame control prior is additionally coded to better preserve finer structure and semantics of each non-keyframe. Guided by these priors, non-keyframes are reconstructed by controllable video generation model with temporal and content consistency. Furthermore, to accurately recover color information of the video, we develop a color-distance-guided keyframe selection algorithm to adaptively choose keyframes. Experimental results show CGVC outperforms previous perceptual video compression method in terms of both signal fidelity and perceptual quality.
title Controllable Generative Video Compression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.06655