Learning to Recover 3D Scene Shape from a Single Image

Benchmark Model Rank Results
depth-estimation-on-scannetv2LeReS#3absolute relative error: 0.095
monocular-depth-estimation-on-eth3dLeReS#8Delta < 1.25: 0.0777absolute relative error: 0.0171
monocular-depth-estimation-on-nyu-depth-v2LeReS#37absolute relative error: 0.09Delta < 1.25: 0.916
monocular-depth-estimation-on-kitti-eigen-splitLeReS#70absolute relative error: 0.149Delta < 1.25: 0.784