Self-supervised intrinsic image decomposition
Name
7175-self-supervised-intrinsic-image-decomposition.pdf
Description
Published version
Size
5.91 MB
Format
Adobe PDF
Checksum (MD5)
ecc19efb319181bc80d2156d49c0323a
Author(s)
Janner, Michael
Wu, Jiajun
Kulkarni, Tejas Dattatraya
Yildirim, Ilker
Tenenbaum, Joshua B
Date Issued
2017
Journal
Advances in Neural Information Processing Systems
Publisher
Neural Information Processing Systems Foundation, Inc.
Citation
Janner, Michael et al. "Self-supervised intrinsic image decomposition." Advances in Neural Information Processing Systems 30: Proceedings of Neural Information Processing Systems 2017, Long Beach, California, edited by I. Guyon, et al. San Diego: Neural Information Processing Systems Foundation. 2017: https://papers.nips.cc/paper/7175-self-supervised-intrinsic-image-decomposition ©2017 Author(s)
Version
Final published version
Abstract
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning intrinsic image decomposition by explaining the input image. Our model, the Rendered Intrinsics Network (RIN), joins together an image decomposition pipeline, which predicts reflectance, shape, and lighting conditions given a single image, with a recombination function, a learned shading model used to recompose the original input based off of intrinsic image predictions. Our network can then use unsupervised reconstruction error as an additional signal to improve its intermediate representations. This allows large-scale unlabeled data to be useful during training, and also enables transferring learned knowledge to images of unseen object categories, lighting conditions, and shapes. Extensive experiments demonstrate that our method performs well on both intrinsic image decomposition and knowledge transfer.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7175-self-supervised-intrinsic-image-decomposition
