Surface Normals in the Wild
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Apr 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 2; 2023: 0; 2024: 2; 2025: 1.
8 papers.
- 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
- 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
- 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
- 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
- 2022Egocentric Scene Understanding via Multimodal Spatial Rectifiercited by 7
- 2024Scale-Invariant Monocular Depth Estimation via SSI Depthcited by 4
- 2025JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localizationcited by 2
- 2022Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understandingcited by 1
- 2025JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization6 Sep 2025
- 2024Scale-Invariant Monocular Depth Estimation via SSI Depth13 Jun 2024
- 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation22 Mar 2024
- 2022Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding9 Dec 2022
- 2022Egocentric Scene Understanding via Multimodal Spatial Rectifier14 Jul 2022
- 2021Shape from Polarization for Complex Scenes in the Wild21 Dec 2021
- 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans11 Oct 2021
- 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction22 Mar 2021