Camera Pose Estimation On Kitti Odometry

Métriques

Absolute Trajectory Error [m]

Average Rotational Error er[%]

Average Translational Error et[%]

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
Monodepth2	93.04	20.72	43.21	Digging Into Self-Supervised Monocular Depth Estimation
SfMLearner	72.57	12.26	29.78	Unsupervised Learning of Depth and Ego-Motion from Video
GeoNet	100.75	9.40	26.31	GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
SC-Depth	37.61	5.11	12.20	Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
DeepMatchVO	25.76	4.85	11.05	Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
SCIPaD	20.83	3.17	8.63	SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
Manydepth2	-	2.205	7.15	Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes

0 of 7 row(s) selected.