{"ID":2890726,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18046","arxiv_id":"2507.18046","title":"Enhancing Scene Transition Awareness in Video Generation via Post-Training","abstract":"Recent advances in AI-generated video have shown strong performance on \\emph{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 \\textbf{Transition-Aware Video} (TAV) dataset, which consists of preprocessed video clips with multiple scene transitions. Our experiment shows that post-training on the \\textbf{TAV} dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.","short_abstract":"Recent advances in AI-generated video have shown strong performance on \\emph{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 p...","url_abs":"https://arxiv.org/abs/2507.18046","url_pdf":"https://arxiv.org/pdf/2507.18046v1","authors":"[\"Hanwen Shen\",\"Jiajie Lu\",\"Yupeng Cao\",\"Xiaonan Yang\"]","published":"2025-07-24T02:50:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}