Logo image
Back
Single Image Multimaterial Estimation
Conference proceeding

Single Image Multimaterial Estimation

Stephen Lombardi, Ko Nishino and IEEE
2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), pp 238-245
01 Jan 2012
DOI: https://doi.org/10.1109/CVPR.2012.6247681

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Interdisciplinary Applications Engineering Engineering, Electrical & Electronic Science & Technology Technology
Estimating the reflectance and illumination from a single image becomes particularly challenging when the object surface consists of multiple materials. The key difficulty lies in recovering the reflectance from sparse angular samples while correctly assigning them to different materials. We tackle this problem by extracting and fully leveraging reflectance priors. The idea is to strongly constrain the possible solutions so that the recovered reflectance conform with those of real-world materials. We achieve this by modeling the parameter space of a directional statistics BRDF model and by extracting an analytical distribution of the subspace that real-world materials span. This is used, with other priors, in a layered MRF-based formulation that models material regions and their spatially varying reflectance with continuous latent layers. The material regions and their reflectance, and the direction and strength of a single point source are jointly estimated. We demonstrate the effectiveness of the method on real and synthetic images.

Metrics

12 Record Views
20 citations in Web of Science
28 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Artificial Intelligence
Computer Science, Interdisciplinary Applications
Engineering, Electrical & Electronic
Logo image