Deep Photometric Stereo Network with Multi-Scale Feature Aggregation.

ABSTRACT: We present photometric stereo algorithms robust to non-Lambertian reflection, which are based on a convolutional neural network in which surface normals of objects with complex geometry and surface reflectance are estimated from a given set of an arbitrary number of images. These images are taken from the same viewpoint under different directional illumination conditions. The proposed method focuses on surface normal estimation, where multi-scale feature aggregation is proposed to obtain a more accurate surface normal, and max pooling is adopted to obtain an intermediate order-agnostic representation in the photometric stereo scenario. The proposed multi-scale feature aggregation scheme using feature concatenation is easily incorporated into existing photometric stereo network architecture

SUBMITTER: Yu C 

PROVIDER: S-EPMC7675179 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature