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（Photometric Stereo, PS）问题旨在通过在不同光照方向下拍摄的一组照片重建物体的三维表面。本文提出了一种用于PS的多尺度架构，该架构结合新数据集，取得了最优结果。该架构具有灵活性：可在不损失性能的前提下，处理可变数量的图像及不同分辨率的图像。此外，我们定义了一组约束条件，以生成适用于PS问题的卷积神经网络训练的相关合成数据集。所提出的数据集规模远超现有数据集，包含大量具有各向异性反射（如金属、玻璃）等挑战性材质的物体。在公开基准上的实验表明，与先前的先进方法相比，这两项贡献的结合显著提升了法向场估算的准确性。