[论文] FracGen: Learning How Objects Stretch and Tear with Physics-Informed V...

论文概要

研究领域: CV 作者: Trong-Tung Nguyen, Jiahan Zhang, Anand Bhattad 发布时间: 2026-09-29 arXiv: 2609.38152

中文摘要

我们提出FracGen——一种断裂感知的视频生成模型，从完整物体的单张图像出发，以物理信号为条件，生成合理、可控的断裂动力学。为训练FracGen，我们构建了FracSim——一个断裂感知仿真框架，用连续损伤模型增强物质点法（MPM）仿真，以标准渲染之外的零额外成本生成配对的断裂视频和密集的像素对齐物理场。FracGen以两种方式利用这些图：它接受联合预测物理场与RGB视频的训练，促使模型捕捉物理状态而非表面外观；并通过物理知情损失监督预测图之间的一致性。因此，FracGen无需昂贵的测试时仿真或按场景调参即可捕捉材料特有的断裂行为，同时提供对物体撕裂位置、裂纹扩展速度和断裂前变形量的细粒度控制。我们进一步引入了一个评估生成断裂视频物理合理性的基准，并通过大量实验表明FracGen在物理和视觉保真度上均优于现有视频生成基线。结果最佳观看方式为项目网站。

原文摘要

We introduce FracGen, a fracture-aware video generation model that produces plausible, controllable fracture dynamics from a single image of an intact object, conditioned on physics signals. To train FracGen, we build FracSim, a fracture-aware simulation framework that augments material point method (MPM) simulation with a continuum damage model, producing paired fracture videos and dense, pixel-aligned physical fields at no additional cost beyond standard rendering. FracGen leverages these maps in two ways: it is trained to jointly predict them alongside RGB video, encouraging the model to capture physical state rather than surface appearance; and it is supervised with physics-informed losses that encourage consistency among the predicted maps. As a result, FracGen captures distinct mater...

#论文 #arXiv #CV #小凯