arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.07007cs.CV
收藏

将创造力扎根于物理:AIGC中物理先验的简要综述

Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC

University of Nevada, Reno(内华达大学里诺分校);Zhejiang University(浙江大学)

Siwei Meng, Yawei Luo, Ping Liu

AI总结:

本文综述了将物理先验融入3D和4D生成的方法,按表示类型分类并比较其优劣,旨在提升AIGC的结构完整性与运动真实感。

摘要:

近年来,AI生成内容(AIGC)的进展显著提升了3D和4D生成的逼真度。然而,现有大多数方法优先考虑外观一致性,却忽略了底层物理原理,导致出现不真实的形变、不稳定的动力学以及不合理的物体交互等伪影。将物理先验融入生成模型已成为增强结构完整性和运动真实感的关键研究方向。本综述回顾了物理感知的生成方法,系统分析了物理约束如何被整合到3D和4D生成中。首先,我们考察了将物理先验融入静态和动态3D生成的近期工作,并根据表示类型对方法进行分类,包括基于视觉的方法、基于NeRF的方法和基于高斯泼溅(Gaussian Splatting)的方法。其次,我们探索了4D生成中的新兴技术,重点关注通过物理仿真建模时间动态的方法。最后,我们对主要方法进行了比较分析,突出它们的优势、局限性以及对不同材料和运动动态的适用性。通过对基于物理的AIGC进行深入分析,本综述旨在弥合生成模型与物理真实感之间的差距,为未来物理一致的生成内容研究提供启发。

英文摘要:

Recent advancements in AI-generated content have significantly improved the realism of 3D and 4D generation. However, most existing methods prioritize appearance consistency while neglecting underlying physical principles, leading to artifacts such as unrealistic deformations, unstable dynamics, and implausible objects interactions. Incorporating physics priors into generative models has become a crucial research direction to enhance structural integrity and motion realism. This survey provides a review of physics-aware generative methods, systematically analyzing how physical constraints are integrated into 3D and 4D generation. First, we examine recent works in incorporating physical priors into static and dynamic 3D generation, categorizing methods based on representation types, including vision-based, NeRF-based, and Gaussian Splatting-based approaches. Second, we explore emerging techniques in 4D generation, focusing on methods that model temporal dynamics with physical simulations. Finally, we conduct a comparative analysis of major methods, highlighting their strengths, limitations, and suitability for different materials and motion dynamics. By presenting an in-depth analysis of physics-grounded AIGC, this survey aims to bridge the gap between generative models and physical realism, providing insights that inspire future research in physically consistent content generation.

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。

↑