Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

Benchmark Model Rank Results
monocular-depth-estimation-on-kitti-eigen-1FeatDepth-MS#21absolute relative error: 0.099RMSE: 4.427RMSE log: 0.184
monocular-depth-estimation-on-kitti-eigen-1FeatDepth-M#28absolute relative error: 0.104