Full BRDF Reconstruction Using CNNs From Partial Photometric Stereo-Light Field Data

Doris Antensteiner, Svorad Stolc; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 13-21

The acquisition of partial BRDF measurements using light field cameras and several illumination directions raises critical questions regarding the accuracy of inferences based on that data. Therefore, we attempt to verify the quality of the reconstruction of a full BRDF using partial input data. A dataset that provides a densely sampled BRDF was used, both in viewing and illumination directions. We show the reconstruction of dense BRDFs when the viewing angles are limited to top central regions, while the illumination angles are not reduced and are positioned in the shape of a half sphere around the material object, these properties are characteristic of data provided by plenoptic cameras paired with a photometric light dome. The partial reconstruction of the dense BRDF out of data is achieved by utilizing convolutional neural networks. We obtain a competitive full reconstruction when up to 2/3 of the BRDF is unknown.