User-assisted intrinsic images

• Main Authors: Bousseau, Adrien (Author), Paris, Sylvain (Author), Durand, Fredo (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Association for Computing Machinery, 2012-07-26T19:51:43Z.
• Subjects: Article
• Online Access: Get fulltext

For many computational photography applications, the lighting and materials in the scene are critical pieces of information. We seek to obtain intrinsic images, which decompose a photo into the product of an illumination component that represents lighting effects and a reflectance component that is the color of the observed material. This is an under-constrained problem and automatic methods are challenged by complex natural images. We describe a new approach that enables users to guide an optimization with simple indications such as regions of constant reflectance or illumination. Based on a simple assumption on local reflectance distributions, we derive a new propagation energy that enables a closed form solution using linear least-squares. We achieve fast performance by introducing a novel downsampling that preserves local color distributions. We demonstrate intrinsic image decomposition on a variety of images and show applications.
National Science Foundation (U.S.) (NSF CAREER award 0447561)
Institut national de recherche en informatique et en automatique (France) (Associate Research Team "Flexible Rendering")
Microsoft Research (New Faculty Fellowship)
Alfred P. Sloan Foundation (Research Fellowship)
Quanta Computer, Inc. (MIT-Quanta T Party)