Multi-view photometric stereo using semi-isometric mappings

Classical uncalibrated Photometric Stereo approaches are mostly constrained to the static view assumption that enforces the camera to be fixed in front of an object illuminated by different light sources. Attempts to extend PS to multi-views has delivered methods that can only be robust to images taken with short camera baselines. In this paper, we present a new uncalibrated Multi-View Photometric Stereo (MVPS) method that can obtain a dense 3D reconstruction from views subject to strong baseline variations and extreme changes in illumination conditions. This approach is intrinsically photo geometric obtaining robust results using a combination of multi-view geometry and photometry. At the core of the algorithm, there is an efficient planar embedding and local image pixel registration among views that renders the problem tractable and computationally solvable. In the experiments, the results are evaluated and compared with the existing methods as well as the ground truth and shows the method is able to deal with the most complex objects and lighting conditions