Depth Estimation on KITTI Eigen split

Metric: absolute relative error (lower is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	absolute relative error▲	Extra Data	Paper	Date↕	Code
1	SPIDepth	0.029	Yes	SPIdepth: Strengthened Pose Information for Self...	2024-04-18	Code
2	UniK3D (FT, metric)	0.037	No	UniK3D: Universal Camera Monocular 3D Estimation	2025-03-20	Code
3	UniDepthV2 (FT, metric)	0.037	Yes	UniDepthV2: Universal Monocular Metric Depth Est...	2025-02-27	Code
4	Metric3Dv2 (g2, FT, 80m, flip_aug_test)	0.039	Yes	Metric3Dv2: A Versatile Monocular Geometric Foun...	2024-03-22	Code
5	LightedDepth (Video Method)	0.041	No	-	-	Code
6	FutureDepth	0.041	No	FutureDepth: Learning to Predict the Future Impr...	2024-03-19	-
7	UniDepth (Zero-shot)	0.042	Yes	UniDepth: Universal Monocular Metric Depth Estim...	2024-03-27	Code
8	SQLdepth (ConvNeXt-L)	0.043	No	SQLdepth: Generalizable Self-Supervised Fine-Str...	2023-09-01	Code
9	AFNet	0.044	No	Adaptive Fusion of Single-View and Multi-View De...	2024-03-12	Code
10	Depth Anything	0.046	Yes	Depth Anything: Unleashing the Power of Large-Sc...	2024-01-19	Code
11	MetaPrompt-SD	0.047	Yes	Harnessing Diffusion Models for Visual Perceptio...	2023-12-22	Code
12	ECoDepth	0.048	No	ECoDepth: Effective Conditioning of Diffusion Mo...	2024-03-27	Code
13	ScaleDepth-K	0.048	No	ScaleDepth: Decomposing Metric Depth Estimation ...	2024-07-11	Code
14	EVP	0.048	No	EVP: Enhanced Visual Perception using Inverse Mu...	2023-12-13	Code
15	GEDepth	0.048	No	GEDepth: Ground Embedding for Monocular Depth Es...	2023-09-18	Code
16	MAMo	0.049	No	MAMo: Leveraging Memory and Attention for Monocu...	2023-07-26	-
17	SwinV2-L 1K-MIM	0.05	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
18	IEBins	0.05	No	IEBins: Iterative Elastic Bins for Monocular Dep...	2023-09-25	Code
19	NDDepth	0.05	No	NDDepth: Normal-Distance Assisted Monocular Dept...	2023-09-19	Code
20	URCDC-Depth	0.05	No	URCDC-Depth: Uncertainty Rectified Cross-Distill...	2023-02-16	Code
21	iDisc	0.05	No	iDisc: Internal Discretization for Monocular Dep...	2023-04-13	Code
22	DDP (Swin-L, step-3)	0.05	No	DDP: Diffusion Model for Dense Visual Prediction	2023-03-30	Code
23	MIM-Swin-V2	0.0508	No	Analysis of NaN Divergence in Training Monocular...	2023-11-07	-
24	PixelFormer	0.051	Yes	Attention Attention Everywhere: Monocular Depth ...	2022-10-17	Code
25	SwinV2-B 1K-MIM	0.052	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
26	BinsFormer	0.052	Yes	BinsFormer: Revisiting Adaptive Bins for Monocul...	2022-04-03	Code
27	NeWCRFs	0.052	Yes	NeW CRFs: Neural Window Fully-connected CRFs for...	2022-03-03	Code
28	DepthFormer	0.052	Yes	DepthFormer: Exploiting Long-Range Correlation a...	2022-03-27	Code
29	MonoDELSNet	0.053	No	Monocular Depth Estimation through Virtual-world...	2021-03-22	Code
30	SfM-Revisited	0.055	No	Deep Two-View Structure-from-Motion Revisited	2021-04-01	Code
31	D-Net	0.056	No	-	-	Code
32	GLPDepth	0.057	No	Global-Local Path Networks for Monocular Depth E...	2022-01-19	Code
33	NVS-MonoDepth	0.057	No	NVS-MonoDepth: Improving Monocular Depth Predict...	2021-12-22	-
34	Depthformer	0.058	Yes	Depthformer : Multiscale Vision Transformer For ...	2022-07-10	Code
35	AdaBins	0.058	Yes	AdaBins: Depth Estimation using Adaptive Bins	2020-11-28	Code
36	Metric3D (zero-shot)	0.058	No	Metric3D: Towards Zero-shot Metric 3D Prediction...	2023-07-20	Code
37	LapDepth	0.059	No	-	-	Code
38	DPT-Hybrid	0.062	No	Vision Transformers for Dense Prediction	2021-03-24	Code
39	BTS	0.064	No	From Big to Small: Multi-Scale Local Planar Guid...	2019-07-24	Code
40	DINOv2 (ViT-g/14 frozen, w/ DPT decoder)	0.0652	No	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
41	LightDepth	0.07	No	LightDepth: A Resource Efficient Depth Estimatio...	2022-11-16	Code
42	DORN	0.072	No	Deep Ordinal Regression Network for Monocular De...	2018-06-06	Code
43	VNL	0.072	No	Enforcing geometric constraints of virtual norma...	2019-07-29	Code
44	PrimeDepth + Depth Anything	0.073	No	PrimeDepth: Efficient Monocular Depth Estimation...	2024-09-13	Code
45	DSN	0.075	No	On Deep Learning Techniques to Boost Monocular D...	2020-10-13	-
46	PrimeDepth	0.079	No	PrimeDepth: Efficient Monocular Depth Estimation...	2024-09-13	Code
47	Focal-WNet	0.082	No	-	-	Code
48	DepthMaster	0.082	Yes	DepthMaster: Taming Diffusion Models for Monocul...	2025-01-05	Code
49	Manydepth2	0.091	No	Manydepth2: Motion-Aware Self-Supervised Multi-F...	2023-12-23	Code
50	VOMonodepth	0.091	No	Enhancing self-supervised monocular depth estima...	2019-08-08	-
51	DenseDepth	0.093	No	High Quality Monocular Depth Estimation via Tran...	2018-12-31	Code
52	SVS	0.094	No	Single View Stereo Matching	2018-03-07	Code
53	monoResMatch	0.096	No	Learning monocular depth estimation infusing tra...	2019-04-08	Code
54	SemiDepth	0.096	No	Semi-Supervised Monocular Depth Estimation with ...	2019-05-18	Code
55	CFA	0.096	No	Monocular Depth Estimation by Learning from Hete...	2018-03-21	-
56	Depth Hints	0.096	No	Self-Supervised Monocular Depth Hints	2019-09-19	Code
57	SOM	0.097	No	Structure-Attentioned Memory Network for Monocul...	2019-09-10	-
58	Marigold	0.099	Yes	Repurposing Diffusion-Based Image Generators for...	2023-12-04	Code
59	GCNDepth	0.104	No	GCNDepth: Self-supervised Monocular Depth Estima...	2021-12-13	Code
60	monodepth2 M	0.106	Yes	Digging Into Self-Supervised Monocular Depth Est...	2018-06-04	Code
61	DeepLabV3+ (F10)	0.11	No	Single Image Depth Estimation Trained via Depth ...	2020-01-14	Code
62	DiPE	0.112	No	DiPE: Deeper into Photometric Errors for Unsuper...	2020-03-03	Code
63	DNet	0.113	No	Toward Hierarchical Self-Supervised Monocular Ab...	2020-04-12	Code
64	LSIM	0.113	No	Learn Stereo, Infer Mono: Siamese Networks for S...	2019-05-01	Code
65	SC-Depth (ResNet 50)	0.114	No	Unsupervised Scale-consistent Depth Learning fro...	2021-05-25	Code
66	SemanticAware	0.118	No	-	-	-
67	SC-Depth (ResNet18)	0.119	No	Unsupervised Scale-consistent Depth Learning fro...	2021-05-25	Code
68	PackNet-SfM	0.12	No	3D Packing for Self-Supervised Monocular Depth E...	2019-05-06	Code
69	3Net	0.126	No	Learning monocular depth estimation with unsuper...	2018-08-05	Code
70	SC-SfMLearner_CS+K	0.128	No	Unsupervised Scale-consistent Depth and Ego-moti...	2019-08-28	Code
71	SelfDepthNorm	0.133	No	Self-supervised Learning for Single View Depth a...	2019-03-01	-
72	SIGNet	0.133	No	SIGNet: Semantic Instance Aided Unsupervised 3D ...	2018-12-13	Code
73	struct2depth	0.135	No	Depth Prediction Without the Sensors: Leveraging...	2018-11-15	Code
74	SC-SfMLearner	0.137	No	Unsupervised Scale-consistent Depth and Ego-moti...	2019-08-28	Code
75	CC	0.14	No	Competitive Collaboration: Joint Unsupervised Le...	2018-05-24	Code
76	SIW	0.14	No	Scaling up Multi-domain Semantic Segmentation wi...	2022-02-04	-
77	LeReS	0.149	No	Learning to Recover 3D Scene Shape from a Single...	2020-12-17	Code
78	GASDA	0.149	No	Geometry-Aware Symmetric Domain Adaptation for M...	2019-04-03	Code
79	VDA	0.193	No	Veritatem Dies Aperit- Temporally Consistent Dep...	2019-03-26	Code

#1SPIDepthSOTA
0.029
absolute relative error· Extra Data· 2024-04-18
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation Code
#2UniK3D (FT, metric)
0.037
absolute relative error· 2025-03-20
UniK3D: Universal Camera Monocular 3D Estimation Code
#3UniDepthV2 (FT, metric)
0.037
absolute relative error· Extra Data· 2025-02-27
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler Code
#4Metric3Dv2 (g2, FT, 80m, flip_aug_test)SOTA
0.039
absolute relative error· Extra Data· 2024-03-22
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation Code
#5LightedDepth (Video Method)
0.041
absolute relative error
No paperCode
#6FutureDepthSOTA
0.041
absolute relative error· 2024-03-19
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
#7UniDepth (Zero-shot)
0.042
absolute relative error· Extra Data· 2024-03-27
UniDepth: Universal Monocular Metric Depth Estimation Code
#8SQLdepth (ConvNeXt-L)SOTA
0.043
absolute relative error· 2023-09-01
SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation Code
#9AFNet
0.044
absolute relative error· 2024-03-12
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving Code
#10Depth Anything
0.046
absolute relative error· Extra Data· 2024-01-19
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Code
#11MetaPrompt-SD
0.047
absolute relative error· Extra Data· 2023-12-22
Harnessing Diffusion Models for Visual Perception with Meta Prompts Code
#12ECoDepth
0.048
absolute relative error· 2024-03-27
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation Code
#13ScaleDepth-K
0.048
absolute relative error· 2024-07-11
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation Code
#14EVP
0.048
absolute relative error· 2023-12-13
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment Code
#15GEDepth
0.048
absolute relative error· 2023-09-18
GEDepth: Ground Embedding for Monocular Depth Estimation Code
#16MAMoSOTA
0.049
absolute relative error· 2023-07-26
MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation
#17SwinV2-L 1K-MIMSOTA
0.05
absolute relative error· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#18IEBins
0.05
absolute relative error· 2023-09-25
IEBins: Iterative Elastic Bins for Monocular Depth Estimation Code
#19NDDepth
0.05
absolute relative error· 2023-09-19
NDDepth: Normal-Distance Assisted Monocular Depth Estimation Code
#20URCDC-Depth
0.05
absolute relative error· 2023-02-16
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation Code
#21iDisc
0.05
absolute relative error· 2023-04-13
iDisc: Internal Discretization for Monocular Depth Estimation Code
#22DDP (Swin-L, step-3)
0.05
absolute relative error· 2023-03-30
DDP: Diffusion Model for Dense Visual Prediction Code
#23MIM-Swin-V2
0.0508
absolute relative error· 2023-11-07
Analysis of NaN Divergence in Training Monocular Depth Estimation Model
#24PixelFormer
0.051
absolute relative error· Extra Data· 2022-10-17
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention Code
#25SwinV2-B 1K-MIM
0.052
absolute relative error· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#26BinsFormer
0.052
absolute relative error· Extra Data· 2022-04-03
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation Code
#27NeWCRFsSOTA
0.052
absolute relative error· Extra Data· 2022-03-03
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation Code
#28DepthFormer
0.052
absolute relative error· Extra Data· 2022-03-27
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation Code
#29MonoDELSNetSOTA
0.053
absolute relative error· 2021-03-22
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision Code
#30SfM-Revisited
0.055
absolute relative error· 2021-04-01
Deep Two-View Structure-from-Motion Revisited Code
#31D-Net
0.056
absolute relative error
No paperCode
#32GLPDepth
0.057
absolute relative error· 2022-01-19
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth Code
#33NVS-MonoDepth
0.057
absolute relative error· 2021-12-22
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
#34Depthformer
0.058
absolute relative error· Extra Data· 2022-07-10
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion Code
#35AdaBinsSOTA
0.058
absolute relative error· Extra Data· 2020-11-28
AdaBins: Depth Estimation using Adaptive Bins Code
#36Metric3D (zero-shot)
0.058
absolute relative error· 2023-07-20
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image Code
#37LapDepth
0.059
absolute relative error
No paperCode
#38DPT-Hybrid
0.062
absolute relative error· 2021-03-24
Vision Transformers for Dense Prediction Code
#39BTSSOTA
0.064
absolute relative error· 2019-07-24
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation Code
#40DINOv2 (ViT-g/14 frozen, w/ DPT decoder)
0.0652
absolute relative error· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#41LightDepth
0.07
absolute relative error· 2022-11-16
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning Code
#42DORNSOTA
0.072
absolute relative error· 2018-06-06
Deep Ordinal Regression Network for Monocular Depth Estimation Code
#43VNL
0.072
absolute relative error· 2019-07-29
Enforcing geometric constraints of virtual normal for depth prediction Code
#44PrimeDepth + Depth Anything
0.073
absolute relative error· 2024-09-13
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage Code
#45DSN
0.075
absolute relative error· 2020-10-13
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation
#46PrimeDepth
0.079
absolute relative error· 2024-09-13
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage Code
#47Focal-WNet
0.082
absolute relative error
No paperCode
#48DepthMaster
0.082
absolute relative error· Extra Data· 2025-01-05
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation Code
#49Manydepth2
0.091
absolute relative error· 2023-12-23
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes Code
#50VOMonodepth
0.091
absolute relative error· 2019-08-08
Enhancing self-supervised monocular depth estimation with traditional visual odometry
#51DenseDepth
0.093
absolute relative error· 2018-12-31
High Quality Monocular Depth Estimation via Transfer Learning Code
#52SVSSOTA
0.094
absolute relative error· 2018-03-07
Single View Stereo Matching Code
#53monoResMatch
0.096
absolute relative error· 2019-04-08
Learning monocular depth estimation infusing traditional stereo knowledge Code
#54SemiDepth
0.096
absolute relative error· 2019-05-18
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network Code
#55CFA
0.096
absolute relative error· 2018-03-21
Monocular Depth Estimation by Learning from Heterogeneous Datasets
#56Depth Hints
0.096
absolute relative error· 2019-09-19
Self-Supervised Monocular Depth Hints Code
#57SOM
0.097
absolute relative error· 2019-09-10
Structure-Attentioned Memory Network for Monocular Depth Estimation
#58Marigold
0.099
absolute relative error· Extra Data· 2023-12-04
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation Code
#59GCNDepth
0.104
absolute relative error· 2021-12-13
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network Code
#60monodepth2 M
0.106
absolute relative error· Extra Data· 2018-06-04
Digging Into Self-Supervised Monocular Depth Estimation Code
#61DeepLabV3+ (F10)
0.11
absolute relative error· 2020-01-14
Single Image Depth Estimation Trained via Depth from Defocus Cues Code
#62DiPE
0.112
absolute relative error· 2020-03-03
DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos Code
#63DNet
0.113
absolute relative error· 2020-04-12
Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications Code
#64LSIM
0.113
absolute relative error· 2019-05-01
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation Code
#65SC-Depth (ResNet 50)
0.114
absolute relative error· 2021-05-25
Unsupervised Scale-consistent Depth Learning from Video Code
#66SemanticAware
0.118
absolute relative error
No paper
#67SC-Depth (ResNet18)
0.119
absolute relative error· 2021-05-25
Unsupervised Scale-consistent Depth Learning from Video Code
#68PackNet-SfM
0.12
absolute relative error· 2019-05-06
3D Packing for Self-Supervised Monocular Depth Estimation Code
#693Net
0.126
absolute relative error· 2018-08-05
Learning monocular depth estimation with unsupervised trinocular assumptions Code
#70SC-SfMLearner_CS+K
0.128
absolute relative error· 2019-08-28
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video Code
#71SelfDepthNorm
0.133
absolute relative error· 2019-03-01
Self-supervised Learning for Single View Depth and Surface Normal Estimation
#72SIGNet
0.133
absolute relative error· 2018-12-13
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception Code
#73struct2depth
0.135
absolute relative error· 2018-11-15
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos Code
#74SC-SfMLearner
0.137
absolute relative error· 2019-08-28
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video Code
#75CC
0.14
absolute relative error· 2018-05-24
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation Code
#76SIW
0.14
absolute relative error· 2022-02-04
Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings
#77LeReS
0.149
absolute relative error· 2020-12-17
Learning to Recover 3D Scene Shape from a Single Image Code
#78GASDA
0.149
absolute relative error· 2019-04-03
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation Code
#79VDA
0.193
absolute relative error· 2019-03-26
Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach Code