Monocular Depth Estimation on KITTI capped 50m 15 (Eigen) benchmark leaderboard · SOTA2 Research

Monocular Depth Estimation on KITTI capped 50m 15 (Eigen)

0.1069Abs RelLearn Stereo, Infer Mono (ResNet)

Evaluation Results

Method
Learn Stereo, Infer Mono (ResNet)2019.05	0.1069	0.6531	3.79	0.195	86.7	95.4	97.9
Godard et al.2019.05	0.108	0.657	3.729	0.194	87.3	95.4	97.9
Learn Stereo, Infer Mono (VGG)2019.05	0.1155	0.7152	3.922	0.201	85.9	95.1	97.9
Kuznietsov et al.2019.04	0.117	0.597	3.531	0.183	86.1	96.4	98.9
Godard et al.2019.04	0.14	0.976	4.471	0.232	81.8	93.1	96.9
GASDA2019.04	0.143	0.756	3.846	0.217	83.6	94.6	97.6
Yin et al.2019.05	0.147	0.936	4.348	0.218	81	94.1	97.7
All real (baseline2)2019.04	0.151	0.856	4.043	0.227	82.4	94	97.3
Kundu et al.2019.04	0.162	1.041	4.344	0.225	78.4	93	97.4
Zheng et al.2019.04	0.168	1.199	4.674	0.243	77.2	91.2	96.6
Garg et al.2017.04	0.169	1.08	5.104	0.273	74	90.4	96.2
Garg et al.2019.04	0.169	1.08	5.104	0.273	74	90.4	96.2
Garg et al.2019.05	0.169	1.08	5.104	0.273	74	90.4	96.2
SfMLearner2017.04	0.19	1.436	4.975	0.258	73.5	91.5	96.8
SfMLearner2017.04	0.201	1.391	5.181	0.264	69.6	90	96.6
Kundu et al.2019.04	0.203	1.734	6.251	0.284	68.7	89.9	95.8
SfMLearner (w/o explainability)2017.04	0.208	1.551	5.452	0.273	69.5	90	96.4
All synthetic (baseline1)2019.04	0.244	1.771	5.354	0.313	64.7	86.6	94.3
SfMLearner2017.04	0.26	2.232	6.148	0.321	59	85.2	94.5