Robust Photometric Stereo Using Learned Image and Gradient Dictionaries

TL;DR

This paper introduces a robust photometric stereo method that employs adaptive dictionary learning to enhance normal vector estimation under noisy conditions, outperforming existing techniques.

Contribution

It presents two novel approaches using adaptive dictionary regularization, one for image preprocessing and another for direct normal vector estimation, improving robustness to noise.

Findings

Both methods achieve state-of-the-art performance in noisy environments.

Extensive simulations validate the effectiveness of the proposed approaches.

The methods outperform existing techniques in robustness to non-idealities.

Abstract

Photometric stereo is a method for estimating the normal vectors of an object from images of the object under varying lighting conditions. Motivated by several recent works that extend photometric stereo to more general objects and lighting conditions, we study a new robust approach to photometric stereo that utilizes dictionary learning. Specifically, we propose and analyze two approaches to adaptive dictionary regularization for the photometric stereo problem. First, we propose an image preprocessing step that utilizes an adaptive dictionary learning model to remove noise and other non-idealities from the image dataset before estimating the normal vectors. We also propose an alternative model where we directly apply the adaptive dictionary regularization to the normal vectors themselves during estimation. We study the practical performance of both methods through extensive simulations, which demonstrate the state-of-the-art performance of both methods in the presence of noise.