VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
This addresses the challenge of coherent video generation for AI applications, though it appears incremental as it builds on existing models with a novel inference-time method.
The paper tackles the problem of video generation models struggling with complex dynamics and coherent consequences by introducing VChain, a chain-of-visual-thought framework that injects visual reasoning from multimodal models into video generation, resulting in significantly enhanced video quality in experiments on multi-step scenarios.
Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over time remains a core challenge. In contrast, large language and multimodal models (e.g., GPT-4o) exhibit strong visual state reasoning and future prediction capabilities. To bridge these strengths, we introduce VChain, a novel inference-time chain-of-visual-thought framework that injects visual reasoning signals from multimodal models into video generation. Specifically, VChain contains a dedicated pipeline that leverages large multimodal models to generate a sparse set of critical keyframes as snapshots, which are then used to guide the sparse inference-time tuning of a pre-trained video generator only at these key moments. Our approach is tuning-efficient, introduces minimal overhead and avoids dense supervision. Extensive experiments on complex, multi-step scenarios show that VChain significantly enhances the quality of generated videos.