MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Single image intrinsic decomposition without a single intrinsic image

Author(s)
Ma, Wei-Chiu; Chu, Hang; Zhou, Bolei; Urtasun, Raquel; Torralba, Antonio
Thumbnail
DownloadAccepted version (7.372Mb)
Terms of use
Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/
Metadata
Show full item record
Abstract
Intrinsic image decomposition-decomposing a natural image into a set of images corresponding to different physical causes-is one of the key and fundamental problems of computer vision. Previous intrinsic decomposition approaches either address the problem in a fully supervised manner, or require multiple images of the same scene as input. These approaches are less desirable in practice, as ground truth intrinsic images are extremely difficult to acquire, and requirement of multiple images pose severe limitation on applicable scenarios. In this paper, we propose to bring the best of both worlds. We present a two stream convolutional neural network framework that is capable of learning the decomposition effectively in the absence of any ground truth intrinsic images, and can be easily extended to a (semi-)supervised setup. At inference time, our model can be easily reduced to a single stream module that performs intrinsic decomposition on a single input image. We demonstrate the effectiveness of our framework through extensive experimental study on both synthetic and real-world datasets, showing superior performance over previous approaches in both single-image and multi-image settings. Notably, our approach outperforms previous state-of-the-art single image methods while using only 50% of ground truth supervision. ©2018 Keywords: intrinsic decomposition; unsupervised learning; self-supervised learning
Date issued
2018-09
URI
https://hdl.handle.net/1721.1/124570
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Journal
European Conference on Computer Vision
Publisher
Springer Nature Switzerland AG
Citation
Ma, Wei-Chiu, et al., "Single image intrinsic decomposition without a single intrinsic image." Computer Vision: ECCV 2018, 15th European Conference on Computer Vision, September 8-14, 2018, Munich, Germany, edited by Vittorio Ferrari et al. Lecture Notes in Computer Science ; 11218 (Cham, Switzerland: Springer, 2018): p. 211-29 doi 10.1007/978-3-030-01264-9_13 ©2018 Author(s)
Version: Author's final manuscript
ISBN
978-3-030-01263-2
978-3-030-01264-9
ISSN
0302-9743
1611-3349

Collections
  • MIT Open Access Articles

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Facebook Instagram YouTube RSS

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.