Zhan, H.Weerasekera, C.S.Garg, R.Reid, I.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.2020-05-012020-05-012019IEEE 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.4811-4817153866027X97815386602631050-47292577-087Xhttp://hdl.handle.net/2440/124480In 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.en©2019 IEEEConference paper100000051010.1109/ICRA.2019.87939840004949423030722-s2.0-85071430160498085Garg, R. [0000-0002-9422-8086]Reid, I. [0000-0001-7790-6423]