The photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object, thanks to a set of photographs taken under different lighting directions. In this paper, we propose a multi-scale architecture for PS which, combined with a new dataset, yields state-of-the-art results. Our proposed architecture is flexible: it permits to consider a variable number of images as well as variable image size without loss of performance. In addition, we define a set of constraints to allow the generation of a relevant synthetic dataset to train convolutional neural networks for the PS problem. Our proposed dataset is much larger than pre-existing ones, and contains many objects with challenging materials having anisotropic reflectance (e.g. metals, glass). We show on publicly available benchmarks that the combination of both these contributions drastically improves the accuracy of the estimated normal field, in comparison with previous state-of-the-art methods.
翻译:光度立体( PS) 问题在于重建一个物体的三维表面, 这是因为在不同的灯光方向下拍摄了一套照片。 在本文中, 我们提议了一个多尺度的 PS 结构, 与新的数据集相结合, 产生最先进的结果。 我们提议的架构是灵活的: 它允许在不失性能的情况下考虑不同数量的图像和可变图像大小。 此外, 我们定义了一组制约, 以便生成一个相关的合成数据集, 用于为 PS 问题培训进化神经网络。 我们提议的数据集比原有的要大得多, 并包含许多具有具有异性反射作用的材料( 如金属、玻璃) 。 我们用公开的基准显示, 这两种贡献的组合与以往最先进的方法相比, 大大提高了估计正常场的准确性。