Self-supervised intrinsic image decomposition
Author(s)Janner, Michael; Wu, Jiajun; Kulkarni, Tejas Dattatraya; Yildirim, Ilker; Tenenbaum, Joshua B
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Advances in Neural Information Processing Systems
Neural Information Processing Systems Foundation, Inc.
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)
Final published version