Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fang, Ye, Wu, Tong, Deschaintre, Valentin, Ceylan, Duygu, Georgiev, Iliyan, Huang, Chun-Hao Paul, Hu, Yiwei, Chen, Xuelin, Wang, Tuanfeng Yang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.11799
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911316135903232
author Fang, Ye
Wu, Tong
Deschaintre, Valentin
Ceylan, Duygu
Georgiev, Iliyan
Huang, Chun-Hao Paul
Hu, Yiwei
Chen, Xuelin
Wang, Tuanfeng Yang
author_facet Fang, Ye
Wu, Tong
Deschaintre, Valentin
Ceylan, Duygu
Georgiev, Iliyan
Huang, Chun-Hao Paul
Hu, Yiwei
Chen, Xuelin
Wang, Tuanfeng Yang
contents Large-scale video generation models have shown remarkable potential in modeling photorealistic appearance and lighting interactions in real-world scenes. However, a closed-loop framework that jointly understands intrinsic scene properties (e.g., albedo, normal, material, and irradiance), leverages them for video synthesis, and supports editable intrinsic representations remains unexplored. We present V-RGBX, the first end-to-end framework for intrinsic-aware video editing. V-RGBX unifies three key capabilities: (1) video inverse rendering into intrinsic channels, (2) photorealistic video synthesis from these intrinsic representations, and (3) keyframe-based video editing conditioned on intrinsic channels. At the core of V-RGBX is an interleaved conditioning mechanism that enables intuitive, physically grounded video editing through user-selected keyframes, supporting flexible manipulation of any intrinsic modality. Extensive qualitative and quantitative results show that V-RGBX produces temporally consistent, photorealistic videos while propagating keyframe edits across sequences in a physically plausible manner. We demonstrate its effectiveness in diverse applications, including object appearance editing and scene-level relighting, surpassing the performance of prior methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11799
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
Fang, Ye
Wu, Tong
Deschaintre, Valentin
Ceylan, Duygu
Georgiev, Iliyan
Huang, Chun-Hao Paul
Hu, Yiwei
Chen, Xuelin
Wang, Tuanfeng Yang
Computer Vision and Pattern Recognition
Large-scale video generation models have shown remarkable potential in modeling photorealistic appearance and lighting interactions in real-world scenes. However, a closed-loop framework that jointly understands intrinsic scene properties (e.g., albedo, normal, material, and irradiance), leverages them for video synthesis, and supports editable intrinsic representations remains unexplored. We present V-RGBX, the first end-to-end framework for intrinsic-aware video editing. V-RGBX unifies three key capabilities: (1) video inverse rendering into intrinsic channels, (2) photorealistic video synthesis from these intrinsic representations, and (3) keyframe-based video editing conditioned on intrinsic channels. At the core of V-RGBX is an interleaved conditioning mechanism that enables intuitive, physically grounded video editing through user-selected keyframes, supporting flexible manipulation of any intrinsic modality. Extensive qualitative and quantitative results show that V-RGBX produces temporally consistent, photorealistic videos while propagating keyframe edits across sequences in a physically plausible manner. We demonstrate its effectiveness in diverse applications, including object appearance editing and scene-level relighting, surpassing the performance of prior methods.
title V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.11799