Surface Normal Estimation

1. Task

Given a single RGB image, recover the pixel-wise surface normals, and decide the relative relations among predicted normals, i.e. orthognal, parallel, or neither.

2. Evaluation Metrics

Absolute Normal Error:

Relative Normal Error:

For a more detailed explanation of the above metrics, please refer to the OASIS paper.

3. Leaderboard

Method Mean Median 11.25° 22.5° 30° AUC o AUC p
Hourglass (OASIS)[1] 23.91 18.16 31.23% 59.45% 71.77% 0.5913 0.5786


Hourglass (OASIS)
Chen, W., Qian, S., Fan, D., Kojima, N., Hamilton, M., & Deng, J. OASIS: A Large-Scale Dataset for Single Image 3D in the Wild. CVPR 2020.