Identifying Surface BRDF From a Single 4-D Light Field Image via Deep Neural Network

Bidirectional reflectance distribution function (BRDF) defines how light is reflected at a surface patch to produce the surface appearance, and thus, modeling/recognizing BRDFs is of great importance for various tasks in computer vision and graphics. However, such tasks are usually ill-posed or require heavy labor on image capture from different viewing angles. In this paper, we focus on the problem of remote BRDF type identification, by delivering novel techniques that capture and use a single light field image. The key is that a light field image captures both the spatial and angular information by a single shot, and the angular information enables effective samplings of the four-dimensional (4-D) BRDF. To implement the idea, we propose convolutional neural network based architectures for BRDF identification from a single 4-D light field image. Specifically, a StackNet and an Ang-convNet are introduced. The StackNet stacks the angular information of the light field images in an independent dimension, whereas the Ang-convNet uses angular filters to encode the angular information. In addition, we propose a large light field BRDF dataset containing 47 650 high-quality 4-D light field image patches, with different 3-D shapes, BRDFs, and illuminations. Experimental results show significant accuracy improvement in BRDF identification by using the proposed methods.