We present a novel convolutional neural network architecture for photometric stereo (Woodham, 1980), a problem of recovering 3D object surface normals from multiple images observed under varying illuminations. Despite its long history in computer vision, the problem still shows fundamental challenges for surfaces with unknown general reflectance properties (BRDFs). Leveraging deep neural networks to learn complicated reflectance models is promising, but studies in this direction are very limited due to difficulties in acquiring accurate ground truth for training and also in designing networks invariant to permutation of input images. In order to address these challenges, we propose a reconstruction based unsupervised learning framework where surface normals and BRDFs are predicted by the network and fed into the rendering equation to synthesize observed images. The network is trained during testing by minimizing reconstruction loss between observed and synthesized images. Thus, our learning process does not require ground truth normals or even pre-training on external images. Our method is shown to achieve the state-of-the-art performance on a challenging real-world scene benchmark.

本研究提出了一种用于光度立体图像的卷积神经网络结构，通过物理学建模的无监督学习框架，可以进行表面法线和反射率预测，并且在实际场景中达到了最先进的性能表现。

通用反射光度立体的神经反渲染