Monocular Depth Estimation On Kitti Eigen 1

评估指标

Delta u003c 1.25

Delta u003c 1.25^2

Delta u003c 1.25^3

Mono

RMSE

RMSE log

Sq Rel

absolute relative error

评测结果

各个模型在此基准测试上的表现结果

									Paper Title	Repository
Struct2Depth M	-	-	-	-	-	-	-	0.1412	Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics	-
Monodepth S	-	-	-	-	-	-	-	0.133	Unsupervised Monocular Depth Estimation with Left-Right Consistency
Monodepth2 M	-	-	-	-	-	-	-	0.115	Digging Into Self-Supervised Monocular Depth Estimation	-
Dyna-DM	0.871	0.959	0.982	-	4.698	0.192	0.785	0.115	Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
pc4consistentdepth	-	-	-	-	-	-	-	0.113	Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
Occlusion_mask_640x192	-	-	-	-	-	-	-	0.113	Improving Self-Supervised Single View Depth Estimation by Masking Occlusion
SuperDepth S	-	-	-	-	-	-	-	0.112	SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation	-
DCPI-Depth (M+832x256+SC-V3)	-	-	-	-	4.496	-	0.679	0.109	DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation	-
HR-Depth-M-640x192	-	-	-	-	-	-	-	0.109	HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
SharinGAN	0.864	0.954	0.981	-	3.77	0.19	0.673	0.109	SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
G2S (MD2-M-R18-pp-640 x 192)	-	-	-	-	-	-	-	0.109	Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation
Monodepth2 S	-	-	-	-	-	-	-	0.109	Digging Into Self-Supervised Monocular Depth Estimation	-
PackNet-SfM M	-	-	-	-	-	-	-	0.107	3D Packing for Self-Supervised Monocular Depth Estimation
CamLessMonoDepth (V2)-640x192	-	-	-	-	-	-	-	0.106	CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters	-
Monodepth2 MS	-	-	-	-	-	-	-	0.106	Digging Into Self-Supervised Monocular Depth Estimation	-
CamLessMonoDepth (V1)-640x192	-	-	-	-	-	-	-	0.105	CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters	-
VTDepthB2 (monocular supervision)	0.893	0.964	0.983	-	4.530	0.182	0.762	0.105	Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation	-
GCNDepth	-	-	-	-	4.494	0.181	0.720	0.104	GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network
Lite-HR-Depth-T-1280x384	-	-	-	-	-	-	-	0.104	HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
MonoFormer	-	-	-	O	-	-	-	0.104	Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation

0 of 54 row(s) selected.