PS-FCN: a flexible learning framework for photometric stereo

Conference item

This paper addresses the problem of photometric stereo for non-Lambertian surfaces. Existing approaches often adopt simplified reflectance models to make the problem more tractable, but this greatly hinders their applications on real-world objects. In this paper, we propose a deep fully convolutional network, called PS-FCN, that takes an arbitrary number of images of a static object captured under different light directions with a fixed camera as input, and predicts a normal map of the object in a fast feed-forward pass. Unlike the recently proposed learning based method, PS-FCN does not require a pre-defined set of light directions during training and testing, and can handle multiple images and light directions in an order-agnostic manner. Although we train PS-FCN on synthetic data, it can generalize well on real datasets. We further show that PS-FCN can be easily extended to handle the problem of uncalibrated photometric stereo. Extensive experiments on public real datasets show that PS-FCN outperforms existing approaches in calibrated photometric stereo, and promising results are achieved in uncalibrated scenario, clearly demonstrating its effectiveness.

Authors: Chen, G; Han, K; Wong, K

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Verlag
• Host title: Computer Vision – ECCV 2018 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part I
• Journal: Lecture Notes in Computer Science
• Volume: 11213
• Pages: 3-19
• Series: Lecture Notes in Computer Science
• Publication date: 2018-10-05
• Acceptance date: 2018-07-03
• DOI: 10.1007/978-3-030-01240-3_1
• EISSN: 1611-3349
• ISSN: 0302-9743
• ISBN: 9783030012397
• Keywords: convolutional neural network; photometric stereo