Shadow Estimation Method for "The Episolar Constraint: Monocular Shape from Shadow Correspondence"

TL;DR

This paper presents a parameter-free EM-based method for accurate shadow estimation in long-term time-lapse sequences, improving shape recovery and photometric stereo performance.

Contribution

It introduces a novel EM approach that jointly estimates shadows, albedo, normals, and skylight without tuning parameters, outperforming previous methods.

Findings

More accurate shadow masks than prior methods.

Effective over both short and long sequences.

Enhances sun-based photometric stereo results.

Abstract

Recovering shadows is an important step for many vision algorithms. Current approaches that work with time-lapse sequences are limited to simple thresholding heuristics. We show these approaches only work with very careful tuning of parameters, and do not work well for long-term time-lapse sequences taken over the span of many months. We introduce a parameter-free expectation maximization approach which simultaneously estimates shadows, albedo, surface normals, and skylight. This approach is more accurate than previous methods, works over both very short and very long sequences, and is robust to the effects of nonlinear camera response. Finally, we demonstrate that the shadow masks derived through this algorithm substantially improve the performance of sun-based photometric stereo compared to earlier shadow mask estimation.