Saved in:
Bibliographic Details
Main Authors: Li, Yifan, Cheng, Pei, Fu, Bin, Yang, Shuai, Liu, Jiaying
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.13425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917409552596992
author Li, Yifan
Cheng, Pei
Fu, Bin
Yang, Shuai
Liu, Jiaying
author_facet Li, Yifan
Cheng, Pei
Fu, Bin
Yang, Shuai
Liu, Jiaying
contents Video chroma-lux editing, which aims to modify illumination and color while preserving structural and temporal fidelity, remains a significant challenge. Existing methods typically rely on expensive supervised training with synthetic paired data. This paper proposes VibeFlow, a novel self-supervised framework that unleashes the intrinsic physical understanding of pre-trained video generation models. Instead of learning color and light transitions from scratch, we introduce a disentangled data perturbation pipeline that enforces the model to adaptively recombine structure from source videos and color-illumination cues from reference images, enabling robust disentanglement in a self-supervised manner. Furthermore, to rectify discretization errors inherent in flow-based models, we introduce Residual Velocity Fields alongside a Structural Distortion Consistency Regularization, ensuring rigorous structural preservation and temporal coherence. Our framework eliminates the need for costly training resources and generalizes in a zero-shot manner to diverse applications, including video relighting, recoloring, low-light enhancement, day-night translation, and object-specific color editing. Extensive experiments demonstrate that VibeFlow achieves impressive visual quality with significantly reduced computational overhead. Our project is publicly available at https://lyf1212.github.io/VibeFlow-webpage.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13425
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VibeFlow: Versatile Video Chroma-Lux Editing through Self-Supervised Learning
Li, Yifan
Cheng, Pei
Fu, Bin
Yang, Shuai
Liu, Jiaying
Computer Vision and Pattern Recognition
Video chroma-lux editing, which aims to modify illumination and color while preserving structural and temporal fidelity, remains a significant challenge. Existing methods typically rely on expensive supervised training with synthetic paired data. This paper proposes VibeFlow, a novel self-supervised framework that unleashes the intrinsic physical understanding of pre-trained video generation models. Instead of learning color and light transitions from scratch, we introduce a disentangled data perturbation pipeline that enforces the model to adaptively recombine structure from source videos and color-illumination cues from reference images, enabling robust disentanglement in a self-supervised manner. Furthermore, to rectify discretization errors inherent in flow-based models, we introduce Residual Velocity Fields alongside a Structural Distortion Consistency Regularization, ensuring rigorous structural preservation and temporal coherence. Our framework eliminates the need for costly training resources and generalizes in a zero-shot manner to diverse applications, including video relighting, recoloring, low-light enhancement, day-night translation, and object-specific color editing. Extensive experiments demonstrate that VibeFlow achieves impressive visual quality with significantly reduced computational overhead. Our project is publicly available at https://lyf1212.github.io/VibeFlow-webpage.
title VibeFlow: Versatile Video Chroma-Lux Editing through Self-Supervised Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.13425