Surface Normals in the Wild

2017/04/10 by Chen, Weifeng, Xiang, Donglai, Deng, Jia · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1704.02956

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 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 and our own dataset demonstrate that our approach can significantly improve the quality of depth estimation in the wild.

Cited by

• JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization

Related

• Designing Deep Networks for Surface Normal Estimation
• Self-supervised Learning for Single View Depth and Surface Normal Estimation
• Adaptive Surface Normal Constraint for Depth Estimation
• Single-Image Depth Perception in the Wild
• IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty