Self-supervised learning for single view depth and surface normal estimation
Date
2019
Authors
Zhan, H.
Weerasekera, C.S.
Garg, R.
Reid, I.
Editors
Howard, A.
Althoefer, K.
Arai, F.
Arrichiello, F.
Caputo, B.
Castellanos, J.
Hauser, K.
Isler, V.
Kim, J.
Liu, H.
Oh, P.
Santos, V.
Scaramuzza, D.
Ude, A.
Voyles, R.
Yamane, K.
Okamura, A.
Althoefer, K.
Arai, F.
Arrichiello, F.
Caputo, B.
Castellanos, J.
Hauser, K.
Isler, V.
Kim, J.
Liu, H.
Oh, P.
Santos, V.
Scaramuzza, D.
Ude, A.
Voyles, R.
Yamane, K.
Okamura, A.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
IEEE International Conference on Robotics and Automation, 2019 / Howard, A., Althoefer, K., Arai, F., Arrichiello, F., Caputo, B., Castellanos, J., Hauser, K., Isler, V., Kim, J., Liu, H., Oh, P., Santos, V., Scaramuzza, D., Ude, A., Voyles, R., Yamane, K., Okamura, A. (ed./s), vol.2019-May, pp.4811-4817
Statement of Responsibility
Huangying Zhan, Chamara Saroj Weerasekera, Ravi Garg, Ian Reid
Conference Name
IEEE International Conference on Robotics and Automation (ICRA) (20 May 2019 - 24 May 2019 : Montreal, Canada)
Abstract
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image. In contrast to most existing frameworks which represent outdoor scenes as fronto-parallel planes at piecewise smooth depth, we propose to predict depth with surface orientation while assuming that natural scenes have piece-wise smooth normals. We show that a simple depth-normal consistency as a soft-constraint on the predictions is sufficient and effective for training both these networks simultaneously. The trained normal network provides state-of-the-art predictions while the depth network, relying on much realistic smooth normal assumption, outperforms the traditional self-supervised depth prediction network by a large margin on the KITTI benchmark.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
©2019 IEEE