Uncertainty for SVBRDF Acquisition using Frequency Analysis
This addresses uncertainty estimation for SVBRDF acquisition in computer graphics, which is incremental as it builds on existing methods by adding frequency analysis and applications like capture guidance.
The paper tackles the problem of quantifying uncertainty in SVBRDF acquisition from multi-view captures under uncontrolled conditions, resulting in a method that computes uncertainty maps in milliseconds and shows competitive performance with a positive correlation between error and uncertainty.
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.