CVGRMay 25, 2023

Eclipse: Disambiguating Illumination and Materials using Unintended Shadows

arXiv:2305.16321v316 citations
Originality Highly original
AI Analysis

This addresses a fundamental challenge in inverse rendering for computer vision and graphics, enabling more accurate material and lighting estimation from real-world images.

The paper tackles the ill-posed problem of decomposing an object's appearance into materials and illumination, especially for diffuse objects, by exploiting unintended shadows cast by occluders like photographers. It presents a method that recovers precise materials, illumination, and occluder shapes from images, improving conditioning and resolving ambiguities.

Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is especially challenging for diffuse objects: it is ill-conditioned because diffuse materials severely blur incoming light, and it is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination -- even from diffuse objects -- by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes