Depth Estimation on NYUv2 36 (test)

0.108AbsRelVNL

Evaluation results

Method
VNL2020.06	0.108	0.048	0.416	87.5	97.6	99.4
DORN2020.06	0.115	0.051	0.509	82.8	96.5	99.2
Laina et al.2020.06	0.127	0.055	0.573	81.1	95.3	98.8
Auto-Rectify Network (Ours-ARN)2020.06	0.138	0.059	0.532	82	95.6	98.9
Li et al.2020.06	0.143	0.063	0.635	78.8	95.8	99.1
Auto-Rectify Network (Ours-DP)2020.06	0.143	0.06	0.538	81.2	95.1	98.6
P2Net2020.06	0.147	0.062	0.553	80.1	95.1	98.7
Chakrabarti et al.2020.06	0.149	—	0.62	80.6	95.8	98.7
Eigen et al.2020.06	0.158	—	0.641	76.9	95	98.8
P2Net2020.06	0.159	0.068	0.599	77.2	94.2	98.4
SC-Depth2020.06	0.159	0.068	0.608	77.2	93.9	98.2
Monodepth22020.06	0.176	0.074	0.639	73.4	93.7	98.3
Roy et al.2020.06	0.187	0.078	0.744	—	—	—
TrainFlow2020.06	0.189	0.079	0.686	70.1	91.2	97.8
MovingIndoor2020.06	0.208	0.086	0.712	67.4	90	96.8
Liu et al.2020.06	0.213	0.087	0.759	65	90.6	97.6
Wang et al.2020.06	0.22	0.094	0.745	60.5	89	97
Li et al.2020.06	0.232	0.094	0.821	62.1	88.6	96.8
Liu et al.2020.06	0.335	0.127	1.06	—	—	—
Make3D2020.06	0.349	—	1.214	44.7	74.5	89.7
Depth Transfer2020.06	0.349	0.131	1.21	—	—	—
Ladicky et al.2020.06	—	—	—	54.2	82.9	94.1