4DCodeBench：用代码生成评估智能体 4D 逆向图形能力
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
一个新的开源基准，让智能体看视频写图形程序来重建动态场景，测下来连前沿模型在流体、断裂这类动态上都翻车，做视觉和智能体评测的可以看看。
4DCodeBench 是一个通过代码生成评估 4D 逆向图形的基准，要求智能体从视频重建动态场景并输出可执行的图形程序。测试集包含真实视频和涵盖形变、流体、断裂等物理现象的合成场景。对多个前沿模型的评测显示，静态重建能力强并不代表能可靠重建复杂动态。基准已在 GitHub 开源。
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To accomplish this, agents must translate visual observations into compact representations of scene structure and dynamics, by implementing abstractions such as physical simulations to reproduce complex behavior. To evaluate this capability, we curate a set of real-world videos and construct synthetic scenes spanning diverse physical phenomena, including deformation, fluid flow, and fracture. We perform extensive benchmarking of frontier models, finding that strong static reconstruction capabilities do not yet translate into reliable reconstruction of complex dynamics. 4DCodeBench provides a testbed for tracking progress toward agents that can interpret the dynamics of the world through code. Our benchmark is available at https://github.com/4DCodeBench/4DCodeBench
