Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
3D
/
KITTI Eigen split unsupervised
3D on KITTI Eigen split unsupervised
Metric: Sq Rel (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Sq Rel (best first)
Sq Rel (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Sq Rel
▼
Augmentations
Paper
Date
↕
Code
1
Dyna-DM
0.785
No
Dyna-DM: Dynamic Object-aware Self-supervised Mo...
2022-06-08
Code
2
VTDepthB2 (monocular supervision)
0.762
No
-
-
Code
3
EPCDepth(S+640x192)
0.754
No
Excavating the Potential Capacity of Self-Superv...
2021-09-26
Code
4
VTDepthB2 (stereo supervision)
0.743
No
-
-
Code
5
Nimbled-MD2-R18
0.739
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
6
Nimbled-SwiftDepth-S
0.733
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
7
SCIPaD(M+640x192)
0.732
No
SCIPaD: Incorporating Spatial Clues into Unsuper...
2024-07-07
Code
8
Nimbled-MD2-R50
0.721
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
9
DynamicDepth (M+640x192)
0.72
No
Disentangling Object Motion and Occlusion for Un...
2022-03-29
Code
10
GCNDepth
0.72
No
GCNDepth: Self-supervised Monocular Depth Estima...
2021-12-13
Code
11
TransDSSL
0.711
No
-
-
Code
12
NimbleD-LiteMono-S
0.709
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
13
MonoDEVSNet
0.703
No
Monocular Depth Estimation through Virtual-world...
2021-03-22
Code
14
DS-Depth
0.698
No
DS-Depth: Dynamic and Static Depth Estimation vi...
2023-08-14
Code
15
X-Distill (M+1024x320)
0.698
No
X-Distill: Improving Self-Supervised Monocular D...
2021-10-24
-
16
Nimbled-SwiftDepth
0.697
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
17
FeatDepth-MS
0.697
No
Feature-metric Loss for Self-supervised Learning...
2020-07-21
Code
18
CADepth-Net (MS+1024x320)
0.694
No
Channel-Wise Attention-Based Network for Self-Su...
2021-12-24
Code
19
ProDepth(M+640x192)
0.693
No
ProDepth: Boosting Self-Supervised Multi-Frame M...
2024-07-12
Code
20
NimbleD-LiteMono
0.684
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
21
DCPI-Depth (M+832x256+SC-V3)
0.679
No
DCPI-Depth: Explicitly Infusing Dense Correspond...
2024-05-27
-
22
DIFFNet (MS+1024x320)
0.678
No
Self-Supervised Monocular Depth Estimation with ...
2021-10-18
Code
23
Manydepth2-NF(M+640x192)
0.676
No
Manydepth2: Motion-Aware Self-Supervised Multi-F...
2023-12-23
Code
24
SharinGAN
0.673
No
SharinGAN: Combining Synthetic and Real Data for...
2020-06-07
Code
25
MonoViT(MS+1024x320)
0.671
No
MonoViT: Self-Supervised Monocular Depth Estimat...
2022-08-06
Code
26
DCPI-Depth (M+640x192)
0.662
No
DCPI-Depth: Explicitly Infusing Dense Correspond...
2024-05-27
-
27
DCPI-Depth (M+1024x320)
0.655
No
DCPI-Depth: Explicitly Infusing Dense Correspond...
2024-05-27
-
28
SCIPaD
0.65
No
SCIPaD: Incorporating Spatial Clues into Unsuper...
2024-07-07
Code
29
Manydepth2(M+640x192)
0.649
No
Manydepth2: Motion-Aware Self-Supervised Multi-F...
2023-12-23
Code
30
EPCDepth(S+1024x320)
0.646
No
Excavating the Potential Capacity of Self-Superv...
2021-09-26
Code
31
NimbleD-LiteMono-8M
0.646
No
NimbleD: Enhancing Self-supervised Monocular Dep...
2024-08-26
Code
32
ProDepth
0.629
No
ProDepth: Boosting Self-Supervised Multi-Frame M...
2024-07-12
Code
33
CREMono(M + 1024x320 + Res50)
0.624
No
-
-
-
34
Jasmine
0.581
No
Jasmine: Harnessing Diffusion Prior for Self-sup...
2025-03-20
-
35
PlaneDepth (S + 1280x384)
0.549
No
PlaneDepth: Self-supervised Depth Estimation via...
2022-10-04
Code
36
SPIdepth
0.531
No
SPIdepth: Strengthened Pose Information for Self...
2024-04-18
Code
#1
Dyna-DM
SOTA
0.785
Sq Rel
· 2022-06-08
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
Code
#2
VTDepthB2 (monocular supervision)
0.762
Sq Rel
No paper
Code
#3
EPCDepth(S+640x192)
SOTA
0.754
Sq Rel
· 2021-09-26
Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
Code
#4
VTDepthB2 (stereo supervision)
0.743
Sq Rel
No paper
Code
#5
Nimbled-MD2-R18
0.739
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#6
Nimbled-SwiftDepth-S
0.733
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#7
SCIPaD(M+640x192)
0.732
Sq Rel
· 2024-07-07
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
Code
#8
Nimbled-MD2-R50
0.721
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#9
DynamicDepth (M+640x192)
0.72
Sq Rel
· 2022-03-29
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
Code
#10
GCNDepth
0.72
Sq Rel
· 2021-12-13
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network
Code
#11
TransDSSL
0.711
Sq Rel
No paper
Code
#12
NimbleD-LiteMono-S
0.709
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#13
MonoDEVSNet
SOTA
0.703
Sq Rel
· 2021-03-22
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision
Code
#14
DS-Depth
0.698
Sq Rel
· 2023-08-14
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
Code
#15
X-Distill (M+1024x320)
0.698
Sq Rel
· 2021-10-24
X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation
#16
Nimbled-SwiftDepth
0.697
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#17
FeatDepth-MS
SOTA
0.697
Sq Rel
· 2020-07-21
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion
Code
#18
CADepth-Net (MS+1024x320)
0.694
Sq Rel
· 2021-12-24
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
Code
#19
ProDepth(M+640x192)
0.693
Sq Rel
· 2024-07-12
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
Code
#20
NimbleD-LiteMono
0.684
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#21
DCPI-Depth (M+832x256+SC-V3)
0.679
Sq Rel
· 2024-05-27
DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation
#22
DIFFNet (MS+1024x320)
0.678
Sq Rel
· 2021-10-18
Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
Code
#23
Manydepth2-NF(M+640x192)
0.676
Sq Rel
· 2023-12-23
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes
Code
#24
SharinGAN
SOTA
0.673
Sq Rel
· 2020-06-07
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
Code
#25
MonoViT(MS+1024x320)
0.671
Sq Rel
· 2022-08-06
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
Code
#26
DCPI-Depth (M+640x192)
0.662
Sq Rel
· 2024-05-27
DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation
#27
DCPI-Depth (M+1024x320)
0.655
Sq Rel
· 2024-05-27
DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation
#28
SCIPaD
0.65
Sq Rel
· 2024-07-07
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
Code
#29
Manydepth2(M+640x192)
0.649
Sq Rel
· 2023-12-23
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes
Code
#30
EPCDepth(S+1024x320)
0.646
Sq Rel
· 2021-09-26
Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
Code
#31
NimbleD-LiteMono-8M
0.646
Sq Rel
· 2024-08-26
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
Code
#32
ProDepth
0.629
Sq Rel
· 2024-07-12
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
Code
#33
CREMono(M + 1024x320 + Res50)
0.624
Sq Rel
No paper
#34
Jasmine
0.581
Sq Rel
· 2025-03-20
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
#35
PlaneDepth (S + 1280x384)
0.549
Sq Rel
· 2022-10-04
PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
Code
#36
SPIdepth
0.531
Sq Rel
· 2024-04-18
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation
Code