发表机构
Institute for AI; Tsinghua-Bosch Joint ML Center; Tsinghua University（人工智能研究院; 清华-博世机器学习联合中心; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长视频生成中主体一致性问题，提出DynSC-Eval评估框架及基于其奖励的后训练方法，显著降低不一致指标并保持其他能力。
AI 中文摘要
我们认为，随着视频生成扩展到更长的时长，主体一致性应在动态主体集上进行评估。为此，我们引入了DynSC-Eval，一个评估框架，它在可见生命周期内动态跟踪合格主体，并使用六个互补的物体级指标测量局部连续性和全局身份保持，同时显式检测不一致事件。为验证其有效性，我们设计了主动注入不一致事件的合成实验，展示了DynSC-Eval的敏感性以及现有指标的局限性。对5秒、15秒和60秒视频生成中多种模型的评估进一步揭示了被传统指标掩盖的显著主体一致性差异。除评估外，我们从DynSC-Eval构建奖励，并在自动驾驶测试平台上应用DiffusionNFT后训练。在5秒生成中，我们的方法将Wan-2.1-1.3B的六个不一致指标平均降低13.82%，SANA-2B降低5.66%，在I2V模型ReSim上也观察到改进。定性比较进一步证明了我们方法的有效性。然后，我们通过课程学习将生成扩展到10秒和30秒，并表明一致性优化仍然有效，同时基本保持其他能力。
英文摘要
We argue that as video generation extends to longer durations, subject consistency should be evaluated over \textit{dynamic subject sets}. We therefore introduce \textbf{DynSC-Eval}, an evaluation framework that dynamically tracks eligible subjects throughout their visible lifespans and measures local continuity and global identity preservation using six complementary object-level metrics, with explicit detection of inconsistency events. To validate its effectiveness, we design synthetic experiments that actively inject inconsistency events, demonstrating both the sensitivity of DynSC-Eval and the limitations of existing metrics. Evaluations of diverse models on 5s, 15s, and 60s video generation further reveal substantial subject consistency differences that are obscured by conventional metrics. Beyond evaluation, we construct rewards from DynSC-Eval and apply DiffusionNFT post-training in an autonomous-driving testbed. On 5s generation, our approach reduces the six inconsistency metrics by an average of 13.82\% for Wan-2.1-1.3B and 5.66\% for SANA-2B, with improvements also observed on the I2V model ReSim. Qualitative comparisons further demonstrate the effectiveness of our method. We then extend generation to 10s and 30s through curriculum learning and show that consistency optimization remains effective while largely preserving other capabilities.
CommentsProject website: https://dynsc-paper.pages.dev/
