PhysicsGen：生成模型能否从图像中学习以预测复杂的物理关系？

PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?

March 7, 2025

作者: Martin Spitznagel, Jan Vaillant, Janis Keuper

cs.AI

摘要

生成式学习模型在图像到图像转换方面的能力近期取得了显著进展，特别是在估计图像分布间复杂（可操控）映射方面。尽管基于外观的任务，如图像修复或风格迁移，已被深入研究，我们提议探索生成模型在物理模拟背景下的潜力。通过提供一个包含30万对图像的数据集及针对三种不同物理模拟任务的基线评估，我们提出了一个基准来探究以下研究问题：i) 生成模型能否从输入输出图像对中学习复杂的物理关系？ii) 通过替代基于微分方程的模拟，能实现多大的加速？当前不同模型的基线评估结果展示了实现高加速比的潜力（ii），但同时也揭示了在物理正确性方面存在显著局限（i）。这强调了开发新方法以确保物理正确性的必要性。数据、基线模型及评估代码详见http://www.physics-gen.org。

English

The image-to-image translation abilities of generative learning models have recently made significant progress in the estimation of complex (steered) mappings between image distributions. While appearance based tasks like image in-painting or style transfer have been studied at length, we propose to investigate the potential of generative models in the context of physical simulations. Providing a dataset of 300k image-pairs and baseline evaluations for three different physical simulation tasks, we propose a benchmark to investigate the following research questions: i) are generative models able to learn complex physical relations from input-output image pairs? ii) what speedups can be achieved by replacing differential equation based simulations? While baseline evaluations of different current models show the potential for high speedups (ii), these results also show strong limitations toward the physical correctness (i). This underlines the need for new methods to enforce physical correctness. Data, baseline models and evaluation code http://www.physics-gen.org.