3D on KITTI Eigen split

Metric: Sq Rel (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	Sq Rel▼	Augmentations	Paper	Date↕	Code
1	SfM-Revisited	0.224	No	Deep Two-View Structure-from-Motion Revisited	2021-04-01	Code
2	D-Net	0.189	No	-	-	Code
3	Depthformer	0.187	Yes	Depthformer : Multiscale Vision Transformer For ...	2022-07-10	Code
4	DINOv2 (ViT-g/14 frozen, w/ DPT decoder)	0.1797	No	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
5	Manydepth2	0.17	No	Manydepth2: Motion-Aware Self-Supervised Multi-F...	2023-12-23	Code
6	MonoDELSNet	0.161	No	Monocular Depth Estimation through Virtual-world...	2021-03-22	Code
7	DepthFormer	0.158	Yes	DepthFormer: Exploiting Long-Range Correlation a...	2022-03-27	Code
8	NeWCRFs	0.155	Yes	NeW CRFs: Neural Window Fully-connected CRFs for...	2022-03-03	Code
9	BinsFormer	0.151	Yes	BinsFormer: Revisiting Adaptive Bins for Monocul...	2022-04-03	Code
10	PixelFormer	0.149	Yes	Attention Attention Everywhere: Monocular Depth ...	2022-10-17	Code
11	DDP (Swin-L, step-3)	0.148	No	DDP: Diffusion Model for Dense Visual Prediction	2023-03-30	Code
12	SwinV2-B 1K-MIM	0.148	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
13	MIM-Swin-V2	0.1458	No	Analysis of NaN Divergence in Training Monocular...	2023-11-07	-
14	iDisc	0.145	No	iDisc: Internal Discretization for Monocular Dep...	2023-04-13	Code
15	GEDepth	0.142	No	GEDepth: Ground Embedding for Monocular Depth Es...	2023-09-18	Code
16	IEBins	0.142	No	IEBins: Iterative Elastic Bins for Monocular Dep...	2023-09-25	Code
17	URCDC-Depth	0.142	No	URCDC-Depth: Uncertainty Rectified Cross-Distill...	2023-02-16	Code
18	NDDepth	0.141	No	NDDepth: Normal-Distance Assisted Monocular Dept...	2023-09-19	Code
19	ECoDepth	0.139	No	ECoDepth: Effective Conditioning of Diffusion Mo...	2024-03-27	Code
20	SwinV2-L 1K-MIM	0.139	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
21	ScaleDepth-K	0.136	No	ScaleDepth: Decomposing Metric Depth Estimation ...	2024-07-11	Code
22	EVP	0.136	No	EVP: Enhanced Visual Perception using Inverse Mu...	2023-12-13	Code
23	AFNet	0.132	No	Adaptive Fusion of Single-View and Multi-View De...	2024-03-12	Code
24	MAMo	0.13	No	MAMo: Leveraging Memory and Attention for Monocu...	2023-07-26	-
25	MetaPrompt-SD	0.125	Yes	Harnessing Diffusion Models for Visual Perceptio...	2023-12-22	Code
26	Depth Anything	0.121	Yes	Depth Anything: Unleashing the Power of Large-Sc...	2024-01-19	Code
27	FutureDepth	0.117	No	FutureDepth: Learning to Predict the Future Impr...	2024-03-19	-
28	LightedDepth (Video Method)	0.107	No	-	-	Code
29	SQLdepth (ConvNeXt-L)	0.105	No	SQLdepth: Generalizable Self-Supervised Fine-Str...	2023-09-01	Code
30	SPIDepth	0.069	Yes	SPIdepth: Strengthened Pose Information for Self...	2024-04-18	Code

#1SfM-RevisitedSOTA
0.224
Sq Rel· 2021-04-01
Deep Two-View Structure-from-Motion Revisited Code
#2D-Net
0.189
Sq Rel
No paperCode
#3Depthformer
0.187
Sq Rel· Augmentations· 2022-07-10
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion Code
#4DINOv2 (ViT-g/14 frozen, w/ DPT decoder)
0.1797
Sq Rel· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#5Manydepth2
0.17
Sq Rel· 2023-12-23
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes Code
#6MonoDELSNetSOTA
0.161
Sq Rel· 2021-03-22
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision Code
#7DepthFormer
0.158
Sq Rel· Augmentations· 2022-03-27
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation Code
#8NeWCRFs
0.155
Sq Rel· Augmentations· 2022-03-03
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation Code
#9BinsFormer
0.151
Sq Rel· Augmentations· 2022-04-03
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation Code
#10PixelFormer
0.149
Sq Rel· Augmentations· 2022-10-17
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention Code
#11DDP (Swin-L, step-3)
0.148
Sq Rel· 2023-03-30
DDP: Diffusion Model for Dense Visual Prediction Code
#12SwinV2-B 1K-MIM
0.148
Sq Rel· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#13MIM-Swin-V2
0.1458
Sq Rel· 2023-11-07
Analysis of NaN Divergence in Training Monocular Depth Estimation Model
#14iDisc
0.145
Sq Rel· 2023-04-13
iDisc: Internal Discretization for Monocular Depth Estimation Code
#15GEDepth
0.142
Sq Rel· 2023-09-18
GEDepth: Ground Embedding for Monocular Depth Estimation Code
#16IEBins
0.142
Sq Rel· 2023-09-25
IEBins: Iterative Elastic Bins for Monocular Depth Estimation Code
#17URCDC-Depth
0.142
Sq Rel· 2023-02-16
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation Code
#18NDDepth
0.141
Sq Rel· 2023-09-19
NDDepth: Normal-Distance Assisted Monocular Depth Estimation Code
#19ECoDepth
0.139
Sq Rel· 2024-03-27
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation Code
#20SwinV2-L 1K-MIM
0.139
Sq Rel· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#21ScaleDepth-K
0.136
Sq Rel· 2024-07-11
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation Code
#22EVP
0.136
Sq Rel· 2023-12-13
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment Code
#23AFNet
0.132
Sq Rel· 2024-03-12
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving Code
#24MAMo
0.13
Sq Rel· 2023-07-26
MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation
#25MetaPrompt-SD
0.125
Sq Rel· Augmentations· 2023-12-22
Harnessing Diffusion Models for Visual Perception with Meta Prompts Code
#26Depth Anything
0.121
Sq Rel· Augmentations· 2024-01-19
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Code
#27FutureDepth
0.117
Sq Rel· 2024-03-19
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
#28LightedDepth (Video Method)
0.107
Sq Rel
No paperCode
#29SQLdepth (ConvNeXt-L)
0.105
Sq Rel· 2023-09-01
SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation Code
#30SPIDepth
0.069
Sq Rel· Augmentations· 2024-04-18
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation Code