For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

University of Birmingham

Return to search Previous output Next output
Output 50 of 157 in the submission
Output title

Correlation-Based Intrinsic Image Extraction from a Single Image

Type
E - Conference contribution
Name of conference/published proceedings
Computer Vision – ECCV 2010 Subtitle of host publication: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV
Volume number
6314
Issue number
-
First page of article
58
ISSN of proceedings
0302-9743
Year of publication
2010
URL
-
Number of additional authors
2
Additional information

<23>This paper takes a model of how humans separate illumination effects (shading) from surface properties in an image of an object, and derives a new computer vision algorithm to solve this problem. The work is evaluated on two datasets, and is shown to outperform existing methods. One associated dataset we created for this purpose has been downloaded N times. ECCV is one of the three premiere conference venues in Computer Vision, with an acceptance-rate of 27%. This paper has influenced work on intrinsic image recovery at other high-impact venues, including that of Zhao (IEEE PAMI 2012), and Shen (CVPR 2011).

Interdisciplinary
-
Cross-referral requested
-
Research group
A - Artificial Intelligence and Intelligent Robotics
Citation count
1
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-