• DOI:10.2312/SRE.20181172
Corpus ID: 49366443

Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition

@inproceedings{Bi2018DeepHR,
  title={Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition},
  author={S. Bi and Nima Khademi Kalantari and R. Ramamoorthi},
  booktitle={EGSR},
  year={2018}
}

S. Bi, Nima Khademi Kalantari, R. Ramamoorthi

Published in EGSR 2018

Computer Science

Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep convolutional neural network (CNN). Although deep learning (DL) has been recently used to handle this application, the current DL methods train the network only on synthetic images as obtaining ground truth reflectance and shading for real images is difficult… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed