Self-Supervised Intrinsic Image Decomposition

@inproceedings{Janner2017SelfSupervisedII,
  title={Self-Supervised Intrinsic Image Decomposition},
  author={Michael Janner and Jiajun Wu and Tejas D. Kulkarni and Ilker Yildirim and Joshua B. Tenenbaum},
  booktitle={NIPS},
  year={2017}
}

• Michael Janner, Jiajun Wu, +2 authors Joshua B. Tenenbaum
• Published in NIPS 2017

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… CONTINUE READING

View on ArXiv

Save to Library

Create Alert

Cite