Search papers, labs, and topics across Lattice.
This paper introduces VibeFlow, a self-supervised video chroma-lux editing framework that leverages pre-trained video generation models to modify illumination and color. VibeFlow uses a disentangled data perturbation pipeline to adaptively recombine structure from source videos and color-illumination cues from reference images. The method also introduces Residual Velocity Fields and Structural Distortion Consistency Regularization to improve structural preservation and temporal coherence, achieving state-of-the-art results in various video editing tasks without requiring paired training data.
Achieve versatile video editing鈥攔elighting, recoloring, and more鈥攚ithout any paired training data by cleverly repurposing pre-trained video generation models.
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.