TL;DR
VibeFlow is a self-supervised video editing framework that modifies illumination and color while maintaining structure and temporal coherence, eliminating the need for expensive training.
Contribution
It introduces a disentangled data perturbation pipeline and residual velocity fields to enable robust, zero-shot chroma-lux editing across diverse video applications.
Findings
Achieves high-quality visual results in various editing tasks.
Reduces computational overhead compared to existing methods.
Operates effectively without costly supervised training.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
