Surface Normals in the Wild
This work addresses depth estimation for real-world images, which is incremental as it builds on existing methods by incorporating surface normal annotations.
The paper tackles single-image depth estimation for in-the-wild images by using human-annotated surface normals to train a neural network, resulting in significant improvements in depth estimation quality as demonstrated on NYU Depth and a custom dataset.
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.