Uncertainty for SVBRDF Acquisition using Frequency Analysis

TL;DR

This paper introduces a fast frequency domain method to quantify uncertainty in SVBRDF acquisition, enabling improved capture guidance and inpainting by identifying uncertain regions with high accuracy.

Contribution

The paper presents a novel frequency-based approach for rapid uncertainty estimation in SVBRDF acquisition, enhancing analysis speed and accuracy over previous methods.

Findings

Frequency model achieves competitive SVBRDF parameter recovery.

Accelerated entropy computation matches physically-based path tracer results.

Uncertainty correlates positively with reconstruction error.

Abstract

This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the observations contain enough information to reconstruct the appearance properties of a captured object. We study this ambiguity, or uncertainty, using entropy and accelerate the analysis by using the frequency domain, rather than the domain of incoming and outgoing viewing angles. The result is a method that computes a map of uncertainty over an entire object within a millisecond. We find that the frequency model allows us to recover SVBRDF parameters with competitive performance, that the accelerated entropy computation matches results with a physically-based path tracer, and that there is a positive correlation between error and uncertainty. We then show that the uncertainty map can be applied to improve SVBRDF acquisition using capture guidance, sharing information on the surface, and using a diffusion model to inpaint uncertain regions. Our code is available at https://github.com/rubenwiersma/svbrdf_uncertainty.