Surface Normals in the Wild

Weifeng Chen, Donglai Xiang, Jia Deng; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1557-1566

Abstract


We study the problem of single-image depth estimation for images in the wild. We collect human annotated surface normals and use them to help train a neural network that directly predicts pixel-wise depth. We propose two novel loss functions for training with surface normal annotations. Experiments on NYU Depth, KITTI, and our own dataset demonstrate that our approach can significantly improve the quality of depth estimation in the wild.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Chen_2017_ICCV,
author = {Chen, Weifeng and Xiang, Donglai and Deng, Jia},
title = {Surface Normals in the Wild},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}