CADEngBench: CADに見えるが、機能するのか？パラメトリック設計、アセンブリ推論、物理シミュレーションの評価
CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulation
CADモデルが外見だけでなく工学的に正しいかを評価するベンチマークCADEngBenchを提案し、パラメトリック設計、アセンブリ推論、物理シミュレーションの能力を検証した。
著者: Harmanjot Singh, Abhra Dubey, Jorge Alejandro Amador Herrera
分類: cs.AI, cs.CV, cs.LG, cs.RO
原文アブストラクト
A CAD model is not engineering-grade merely because it looks correct. It must satisfy design requirements, respond predictably to parameter changes, support controlled edits, match a reference structural response under a declared analysis, and connect to other parts through valid joints. We present CADEngBench, a two-track benchmark for these capabilities. CADEngBench-P evaluates 300 parametric parts, each used for one zero-to-CAD task and one functional-editing task (600 tasks in total), through boundary-representation (B-Rep) validity, engineering and DFM checks, parameter-family perturbations, functional editing, and matched linear-static FEA in CalculiX. CADEngBench-A evaluates 150 body pairs through ranked joint retrieval, exact face-and-edge grounding, joint-frame prediction, and kinematic verification. Across eight multimodal, code-capable models, editing supplied CAD is substantially easier than generating it, while complex edits and matched FEA remain difficult. Assembly predictions often locate the relevant region but fail to recover the recorded joint or mating entities. These results show that CAD evaluation must test engineering behavior rather than appearance alone.