We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are fed to a multi-view stereo method to enhance 3D reconstruction. The illumination conditions during acquisition and the feature transform are jointly trained on a large amount of synthetic data. We further build a system to reconstruct the geometry and anisotropic reflectance of a variety of challenging objects from hand-held scans. The effectiveness of the system is demonstrated with a lightweight prototype, consisting of a camera and an array of LEDs, as well as an off-the-shelf tablet. Our results are validated against reconstructions from a professional 3D scanner and photographs, and compare favorably with state-of-the-art techniques.

翻译：我们提出了一种新颖框架，能够自动学习从多个非结构视角中聚合与变换光度测量值，生成具有空间区分性与视角不变性的低级特征，并将其输入多视图立体匹配方法以增强三维重建效果。通过大量合成数据联合训练采集过程中的光照条件与特征变换模块。我们进一步构建了一个系统，能够利用手持扫描设备重建多种复杂物体的几何形状与各向异性反射属性。该系统通过包含相机与LED阵列的轻量化原型设备以及市售平板电脑验证了其有效性。我们以专业三维扫描仪与摄影测量结果为基准对重建结果进行验证，并与当前最先进技术相比展现出显著优势。