Names and shades of color for intrinsic image estimation

In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement...

Full description

Saved in:
Bibliographic Details
Main Authors: Serra, M., Penacchio, O., Benavente, R., Vanrell, M.
Format: Conference Proceeding
Language:English
Subjects:
Coherence
Geometry
Image color analysis
Image edge detection
Labeling
Lighting
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement. In this paper, we propose a novel approach that aims to overcome the shortcomings of pure edge-based methods by introducing strong surface descriptors, such as the color-name descriptor which introduces high-level considerations resembling top-down intervention. We also use a second surface descriptor, termed color-shade, which allows us to include physical considerations derived from the image formation model capturing gradual color surface variations. Both color cues are combined by means of a Markov Random Field. The method is quantitatively tested on the MIT ground truth dataset using different error metrics, achieving state-of-the-art performance.
ISSN:1063-6919
DOI:10.1109/CVPR.2012.6247686