SfMLearner

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Camera Pose EstimationonKITTI Odometry Benchmark
Absolute Trajectory Error [m]· 2017-04-25
72.57
best: 20.83 (SCIPaD)
SOTA
Unsupervised Learning of Depth and Ego-Motion from Video arXiv:1704.07813
Camera Pose EstimationonKITTI Odometry Benchmark
Average Rotational Error er[%]· 2017-04-25
12.26
best: 2.205 (Manydepth2)
SOTA
Unsupervised Learning of Depth and Ego-Motion from Video arXiv:1704.07813
Camera Pose EstimationonKITTI Odometry Benchmark
Average Translational Error et[%]· 2017-04-25
29.78
best: 7.15 (Manydepth2)
SOTA
Unsupervised Learning of Depth and Ego-Motion from Video arXiv:1704.07813