Abstract
We present an automated machine learning approach for uncalibrated photometric stereo (PS). Our work aims at discovering lightweight and computationally efficient PS neural networks with excellent surface normal accuracy. Unlike previous uncalibrated deep PS networks, which are handcrafted and carefully tuned, we leverage differentiable neural architecture search (NAS) strategy to find uncalibrated PS architecture automatically. We begin by defining a discrete search space for a light calibration network and a normal estimation network, respectively. We then perform a continuous relaxation of this search space and present a gradient-based optimization strategy to find an efficient light calibration and normal estimation network. Directly applying the NAS methodology to uncalibrated PS is not straightforward as certain task-specific constraints must be satisfied, which we impose explicitly. Moreover, we search for and train the two networks separately to account for the Generalized Bas-Relief (GBR) ambiguity. Extensive experiments on the DiLiGenT dataset show that the automatically searched neural architectures performance compares favorably with the state-of-the-art uncalibrated PS methods while having a lower memory footprint.

Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo Francesco Sarno, Suryansh Kumar, Berk Kaya, Zhiwu Huang, Vittorio Ferrari, Luc Van Gool. IEEE/CVF WACV 2022, Waikoloa, Hawaii, USA.

Light Directions and Intensities on DiLiGenT Benchmark		Surface Normals on DiLiGenT Benchmark

Francesco Sarno

Suryansh Kumar

Berk Kaya

Zhiwu Huang

Vittorio Ferrari

Luc Van Gool

This work was funded by Focused Research Award from Google(CVL, ETH 2019-HE-318, 2019-HE-323). Suryansh Kumar's project is supported by "ETH Zurich Foundation and Google, Project Number: 2019-HE-323" for bringing together best academic and industrial research.