Proprio: 用于物理合理视频生成的潜在自评分与推理时精炼
Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation
AI总结：
提出Proprio，一种无需训练框架，通过分析模型在潜在扰动下的流残差作为自评分信号，结合最佳N搜索和梯度自精炼，提升冻结视频生成器输出的物理合理性。
摘要：
现代视频生成模型在视觉上效果显著，但经常违反基本物理原理。我们提出Proprio，一种无需训练的框架，使冻结的视频生成器能够评估和改进自身输出的物理合理性。受本体感觉（生物对自身运动的感知）启发，Proprio将模型在受控潜在扰动下的流残差视为自评分信号。能被生成器学习到的动力学更好解释的样本会产生更小且更稳定的残差。我们跨时间步和扰动聚合该信号，通过动态时空掩码聚焦于运动相关区域，并将其用于最佳N搜索、基于梯度的自精炼或两者结合。在文本到视频和图像到视频基准测试中，Proprio持续提升物理合理性，在多种设置下优于基于VLM的评分和外部世界模型基线。使用TurboWan2.2，Proprio将Physics-IQ从32.2提升至37.5（+16.5%），VideoPhy2-hard物理常识从45.6提升至55.0（+20.6%）。人类评估进一步显示，在大约三分之二的比较中，评估者更偏好Proprio选择或精炼的视频的物理合理性。这些结果表明，冻结的视频生成器包含可操作的内部信号，用于评估和改进自身输出的物理合理性。
英文摘要：
Modern video generative models produce visually impressive results, yet frequently violate basic physical principles. We propose Proprio, a training-free framework that enables a frozen video generator to assess and improve the physical plausibility of its own outputs. Inspired by proprioception, the biological sense of one's own movement, Proprio treats the model's flow residual under controlled latent perturbations as a self-scoring signal. Samples that are better explained by the generator's learned dynamics induce smaller and more stable residuals. We aggregate this signal across timesteps and perturbations, focus it on motion-relevant regions with a dynamic spatiotemporal mask, and use it for best-of-N search, gradient-based self-refinement, or both. Across text-to-video and image-to-video benchmarks, Proprio consistently improves physical plausibility, outperforming VLM-based scoring, and external world-model baselines in several settings. With TurboWan2.2, Proprio improves Physics-IQ from 32.2 to 37.5 (+16.5%) and VideoPhy2-hard physical commonsense from 45.6 to 55.0 (+20.6%). Human evaluation further shows that raters prefer Proprio-selected or refined videos for physical plausibility in roughly two-thirds of comparisons. These results suggest that frozen video generators contain actionable internal signals for evaluating and improving the physical plausibility of their own outputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
