仅用一张图片快速预测3D物体材料属性，省去重建步骤。
SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents
- 利用预训练3D生成模型的结构化隐空间特征，直接从单张图像推断材料属性。
- 每物体仅需9.9秒，相比以往方法提速120倍，精度相当。
- 适合需要快速数字孪生或物理仿真的研究与工程场景。
估算3D资产的材料属性场对物理仿真、机器人和数字孪生至关重要。现有基于视觉的方法要么计算昂贵且缓慢，要么依赖3D信息。我们提出SLAT-Phys，一种端到端方法，仅从单张RGB图像直接预测3D资产的空间变化材料属性场，无需显式3D重建。该方法利用预训练3D资产生成模型的结构化隐特征，编码丰富的几何与语义先验，并训练轻量级神经解码器估计杨氏模量、密度和泊松比。隐表示中的粗粒度体布局与语义线索使材料估计更准确。实验表明，本方法在预测连续材料参数方面达到与先前方法相当的精度，同时显著降低计算时间。尤其在NVIDIA RTX A5000 GPU上，每物体仅需9.9秒，避免了重建与体素化预处理，相比以往方法提速120倍，实现单图快速材料属性估计。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。