GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

Xiaojuan Qi, Renjie Liao, Zhengzhe Liu, Raquel Urtasun, Jiaya Jia; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 283-291

Abstract


In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image. Building on top of two-stream CNNs, our GeoNet incorporates geometric relation between depth and surface normal via the new depth-to-normal and normal- to-depth networks. Depth-to-normal network exploits the least square solution of surface normal from depth and im- proves its quality with a residual module. Normal-to-depth network, contrarily, refines the depth map based on the con- straints from the surface normal through a kernel regression module, which has no parameter to learn. These two net- works enforce the underlying model to efficiently predict depth and surface normal for high consistency and corre- sponding accuracy. Our experiments on NYU v2 dataset verify that our GeoNet is able to predict geometrically con- sistent depth and normal maps. It achieves top performance on surface normal estimation and is on par with state-of-the- art depth estimation methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Qi_2018_CVPR,
author = {Qi, Xiaojuan and Liao, Renjie and Liu, Zhengzhe and Urtasun, Raquel and Jia, Jiaya},
title = {GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}