Enhancing Scene Transition Awareness in Video Generation via Post-Training

arXiv:2507.18046v2 Announce Type: replace Abstract: Recent advances in AI-generated video have shown strong performance on text-to-video tasks, particularly for short clips depicting a single scene. However, current models struggle to generate longer videos with coherent scene transitions, primarily because they cannot infer when a transition is needed from the prompt. Most open-source models are trained on datasets consisting of single-scene video clips, which limits their capacity to learn and respond to prompts requiring multiple scenes. Developing scene transition awareness is essential for multi-scene generation, as it allows models to identify and segment videos into distinct clips by accurately detecting transitions. To address this, we propose the extbf{Transition-Aware Video} (TAV) dataset, which consists of preprocessed video clips with multiple scene transitions. Our experiment shows that post-training on the extbf{TAV} dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.

Related

• PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
• VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
• CamC2V: Context-aware Controllable Video Generation

Source: arXiv cs.CV | 2026-07-31