Robust Surface Reconstruction from Gradients via Adaptive Dictionary Regularization

TL;DR

This paper presents an adaptive dictionary learning method for robust surface reconstruction from noisy gradient data, effectively capturing surface structure and improving reconstruction quality.

Contribution

It introduces a novel adaptive dictionary regularization technique that enhances surface reconstruction robustness from noisy gradient fields.

Findings

Effective noise robustness demonstrated on synthetic data

Improved surface smoothness and accuracy

Compatible with existing reconstruction methods

Abstract

This paper introduces a novel approach to robust surface reconstruction from photometric stereo normal vector maps that is particularly well-suited for reconstructing surfaces from noisy gradients. Specifically, we propose an adaptive dictionary learning based approach that attempts to simultaneously integrate the gradient fields while sparsely representing the spatial patches of the reconstructed surface in an adaptive dictionary domain. We show that our formulation learns the underlying structure of the surface, effectively acting as an adaptive regularizer that enforces a smoothness constraint on the reconstructed surface. Our method is general and may be coupled with many existing approaches in the literature to improve the integrity of the reconstructed surfaces. We demonstrate the performance of our method on synthetic data as well as real photometric stereo data and evaluate its robustness to noise.