Feature-metric Loss for Self-supervised Learning of Depth and Egomotion
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-kitti-eigen-1
FeatDepth-MS
#21
absolute relative error: 0.099
RMSE: 4.427
RMSE log: 0.184
…
monocular-depth-estimation-on-kitti-eigen-1
FeatDepth-M
#28
absolute relative error: 0.104
Rank counts only results with a code link.