SLAT-Phys: 構造化3D潜在表現からの高速材料特性場予測
SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents
単一のRGB画像から3Dアセットの材料特性場(ヤング率、密度、ポアソン比)を直接推定するエンドツーエンド手法を提案。事前学習済み3D生成モデルの潜在表現を活用し、軽量デコーダで高速かつ高精度な予測を実現。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Rocktim Jyoti Das, Dinesh Manocha
分類: cs.CV, cs.GR, cs.RO
原文アブストラクト
Estimating the material property field of 3D assets is critical for physics-based simulation, robotics, and digital twin generation. Existing vision-based approaches are either too expensive and slow or rely on 3D information. We present SLAT-Phys, an end-to-end method that predicts spatially varying material property fields of 3D assets directly from a single RGB image without explicit 3D reconstruction. Our approach leverages spatially organised latent features from a pretrained 3D asset generation model that encodes rich geometry and semantic prior, and trains a lightweight neural decoder to estimate Young's modulus, density, and Poisson's ratio. The coarse volumetric layout and semantic cues of the latent representation about object geometry and appearance enable accurate material estimation. Our experiments demonstrate that our method provides competitive accuracy in predicting continuous material parameters when compared against prior approaches, while significantly reducing computation time. In particular, SLAT-Phys requires only 9.9 seconds per object on an NVIDIA RTXA5000 GPU and avoids reconstruction and voxelization preprocessing. This results in 120x speedup compared to prior methods and enables faster material property estimation from a single image.
