Monocular Depth Estimation on KITTI 16 (Eigen split) benchmark leaderboard · SOTA2 Research

Monocular Depth Estimation on KITTI 16 (Eigen split)

0.0251Abs Rel ErrorEmbodied Depth Estimation

Evaluation Results

Method	Links
Embodied Depth Estimation2025.03		0.0251	0.0428	1.654	0.048	99.1	99.8	99.9
Metric3D v22025.03		0.039	—	1.766	0.06	98.9	99.8	100
LightedDepth2025.03		0.041	0.107	1.748	0.059	98.9	99.8	99.9
UniDepth2025.03		0.042	—	1.75	0.064	98.6	99.8	99.9
AFNet2025.03		0.044	0.132	1.712	0.069	98	99.7	99.9
Depth Anything2025.03		0.046	0.121	1.869	0.069	98.2	99.8	100
ECoDepth2025.03		0.048	0.139	1.966	0.074	97.9	99.8	100
Wordepth2025.03		0.049	—	2.039	0.074	97.9	99.8	99.9
iDisc2025.03		0.05	0.145	2.067	0.077	97.7	99.7	99.9
URCDC2025.03		0.05	0.142	2.032	0.076	97.7	99.7	99.9
MiM2025.03		0.05	0.139	1.966	0.075	97.7	99.8	99.9
Trap Attention2025.03		0.05	0.128	1.869	0.074	98	99.8	99.9
DepthFormer2025.03		0.052	0.158	2.143	0.079	97.5	99.7	99.9
NeWCRFs2025.03		0.052	0.155	2.129	0.079	97.4	99.7	99.9
Adabins2025.03		0.058	0.19	2.36	0.088	96.4	99.5	99.9
BTS2025.03		0.061	0.261	2.834	0.099	95.4	99.2	99.8
DORN2025.03		0.071	0.268	2.271	0.116	93.6	98.5	99.5
P3Depth2025.03		0.071	0.27	2.842	0.103	95.3	99.3	99.8
VNL2025.03		0.072	—	3.258	0.117	93.8	99	99.8
Eigen2025.03		0.203	1.548	6.307	0.282	70.2	89.8	96.7