Surface Normals Estimation

18 benchmarks39 papers

Surface normal estimation deals with the task of predicting the surface orientation of the objects present inside a scene. Refer to Designing Deep Networks for Surface Normal Estimation (Wang et al.) to get a good overview of several design choices that led to the development of a CNN-based surface normal estimator.

Benchmarks

Surface Normals Estimation on PCPNet

Surface Normals Estimation on Stanford-ORB

Cosine Distance

Surface Normals Estimation on NYU Depth v2

% < 11.25 Mean Angle Error % < 22.5 % < 30 RMSE

Surface Normals Estimation on ScanNetV2

% < 11.25 % < 22.5 % < 30 Mean Angle Error

Surface Normals Estimation on IBims-1

% < 11.25 Mean % < 22.5 % < 30

Surface Normals Estimation on NYU-Depth V2 Surface Normals

Surface Normals Estimation on PASCAL Context

Mean Angle Error

Surface Normals Estimation on Taskonomy