外观
论文arXiv 2610.2109013 天前
RoboCloth：用于神经反射重建的大规模真实布料材料数据集
原文链接：RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction（arXiv 2610.21090 · 发布日期：2026-10-15）
RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction
RoboCloth采集500种真实布料，用机器人控制相机与光照，并以两阶段神经重建在自有留出材料和UBO2014上验证。
核心要点
- 神经材料训练需要覆盖宽视角与光照的真实布料反射数据。
- 机器人控制相机和光照采集校准HDR图像，并用SfM细化位姿。
- 两阶段流程先学习布料材料先验，再为目标材料拟合高分辨率潜变量纹理。
- 数据、标定、观测张量和划分以CC BY 4.0发布于Hugging Face Hub。
验证范围与局限：验证范围为自有数据集留出材料和独立UBO2014基准上的神经反射重建。
英文摘要 (Abstract)
We present RoboCloth, a dataset of 500 real cloth materials captured under flexible, calibrated camera and lighting configurations, where both are robotically controlled during acquisition. Each material is imaged in approximately 580 high-dynamic range frames spanning a wide view-light hemisphere; camera poses are refined via structure-from-motion and aligned to the robot frame, yielding per-material sparse surface geometry and structured per-point reflectance observations ready for neural material training. We demonstrate the value of this data through a two-stage neural reconstruction pipeline: Stage 1 trains a shared MLP decoder on our corpus to learn cloth material priors; Stage 2 then freezes the decoder and fits a dense 2048x2048 latent texture to each target material. Evaluating on held-out materials from our own dataset and on the independent UBO2014 benchmark, we show that a decoder trained on our captures outperforms decoders trained on existing measured reflectance datasets and analytic PBR fitting, transferring to unseen acquisition systems without modification. The dataset, calibration files, observation tensors, and train/test splits are released under CC BY 4.0 on the Hugging Face Hub.
作者：Zhen Li, Haoran Qin, Francesco Di Sario, Daniel Rebain, Andrea Tagliasacchi
来源
本页事实对应的公开页面，以原文为准。