Sora 以惊人的几何一致性生成视频。

摘要

最近开发的 Sora 模型[1] 在视频生成方面展现出卓越的能力，引发了关于其模拟真实世界现象能力的激烈讨论。尽管它越来越受欢迎，但缺乏已建立的指标来定量评估其与真实世界物理的符合度。在本文中，我们引入了一个新的基准，评估生成视频的质量是否遵循真实世界物理原理。我们采用一种方法，将生成的视频转换为 3D 模型，利用这样一个前提，即 3D 重建的准确性在很大程度上取决于视频质量。从 3D 重建的角度来看，我们使用构建的 3D 模型满足的几何约束的忠实度作为一种代理，来衡量生成的视频符合真实世界物理规则的程度。项目页面：https://sora-geometrical-consistency.github.io/

English

The recently developed Sora model [1] has exhibited remarkable capabilities in video generation, sparking intense discussions regarding its ability to simulate real-world phenomena. Despite its growing popularity, there is a lack of established metrics to evaluate its fidelity to real-world physics quantitatively. In this paper, we introduce a new benchmark that assesses the quality of the generated videos based on their adherence to real-world physics principles. We employ a method that transforms the generated videos into 3D models, leveraging the premise that the accuracy of 3D reconstruction is heavily contingent on the video quality. From the perspective of 3D reconstruction, we use the fidelity of the geometric constraints satisfied by the constructed 3D models as a proxy to gauge the extent to which the generated videos conform to real-world physics rules. Project page: https://sora-geometrical-consistency.github.io/

Sora 以惊人的几何一致性生成视频。

Sora Generates Videos with Stunning Geometrical Consistency

摘要

Support