L-DPSNet: Deep Photometric Stereo Network via Local Diffuse Reflectance Maxima

Kanghui Zeng, Chao Xu, Jing Hu, Yushi Li, Zhaopeng Meng

Abstract: Reconstructing surface normal from the reflectance observations of real objects is a challenging issue. Although recent works on photometric stereo exploit various reflectance-normal mapping models, none of them take both illumination and LDR maximum into account. In this paper, we combine a fusion learning network with LDR maxima to recover the normal of the underlying surface. Unlike traditional formalization, the initial normal estimated by solving the generalized bas-relief (GBR) ambiguity is employed to promote the performance of our learning framework. As an uncalibrated photometric stereo network, our method, called L-DPSNet, takes advantage of LDR-derived information in normal prediction. We present the qualitative and quantitative experiments implemented using synthetic and real data to demonstrate the effectiveness of the proposed model.

External IDs:dblp:conf/iconip/ZengX0LM21