3D on NYU-Depth V2

Metric: absolute relative error (lower is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	absolute relative error▲	Augmentations	Paper	Date↕	Code
1	HybridDepth	0.026	No	HybridDepth: Robust Metric Depth Fusion by Lever...	2024-07-26	Code
2	Distill Any Depth	0.043	No	Distill Any Depth: Distillation Creates a Strong...	2025-02-26	Code
3	UniK3D (FT, metric)	0.044	No	UniK3D: Universal Camera Monocular 3D Estimation	2025-03-20	Code
4	UniDepthV2 (FT, metric)	0.046	Yes	UniDepthV2: Universal Monocular Metric Depth Est...	2025-02-27	Code
5	PrimeDepth + Depth Anything	0.046	No	PrimeDepth: Efficient Monocular Depth Estimation...	2024-09-13	Code
6	Metric3Dv2(L, FT)	0.047	Yes	Metric3Dv2: A Versatile Monocular Geometric Foun...	2024-03-22	Code
7	DepthMaster	0.05	Yes	DepthMaster: Taming Diffusion Models for Monocul...	2025-01-05	Code
8	GRIN	0.051	Yes	GRIN: Zero-Shot Metric Depth with Pixel-Level Di...	2024-09-15	-
9	Marigold + E2E FT(zero-shot)	0.052	No	Fine-Tuning Image-Conditional Diffusion Models i...	2024-09-17	Code
10	Marigold	0.055	Yes	Repurposing Diffusion-Based Image Generators for...	2023-12-04	Code
11	Depth Anything	0.056	Yes	Depth Anything: Unleashing the Power of Large-Sc...	2024-01-19	Code
12	UniDepth (Zero-shot)	0.058	Yes	UniDepth: Universal Monocular Metric Depth Estim...	2024-03-27	Code
13	PrimeDepth	0.058	No	PrimeDepth: Efficient Monocular Depth Estimation...	2024-09-13	Code
14	ECoDepth	0.059	No	ECoDepth: Effective Conditioning of Diffusion Mo...	2024-03-27	Code
15	MetaPrompt-SD	0.061	Yes	Harnessing Diffusion Models for Visual Perceptio...	2023-12-22	Code
16	EVP	0.061	No	EVP: Enhanced Visual Perception using Inverse Mu...	2023-12-13	Code
17	TADP	0.062	Yes	Text-image Alignment for Diffusion-based Percept...	2023-09-29	Code
18	FutureDepth	0.063	No	FutureDepth: Learning to Predict the Future Impr...	2024-03-19	-
19	MeSa	0.066	No	MeSa: Masked, Geometric, and Supervised Pre-trai...	2023-10-06	-
20	PolyMaX(ConvNeXt-L)	0.067	Yes	PolyMaX: General Dense Prediction with Mask Tran...	2023-11-09	Code
21	VPD	0.069	No	Unleashing Text-to-Image Diffusion Models for Vi...	2023-03-03	Code
22	NVDS(DPT-L)	0.072	Yes	NVDS+: Towards Efficient and Versatile Neural St...	2023-07-17	Code
23	DMD	0.072	Yes	Zero-Shot Metric Depth with a Field-of-View Cond...	2023-12-20	-
24	ScaleDepth-N	0.074	No	ScaleDepth: Decomposing Metric Depth Estimation ...	2024-07-11	Code
25	DepthGen	0.074	Yes	Monocular Depth Estimation using Diffusion Models	2023-02-28	-
26	ZoeD-M12-N	0.075	Yes	ZoeDepth: Zero-shot Transfer by Combining Relati...	2023-02-23	Code
27	AiT-P(SwinV2-L)	0.076	No	All in Tokens: Unifying Output Space of Visual T...	2023-01-05	Code
28	Gaming for Depth (GfD)	0.08	Yes	-	-	-
29	SwinV2-L 1K-MIM	0.083	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
30	Metric3D (ConvNeXt-Large, Zero-shot testing)	0.083	Yes	Metric3D: Towards Zero-shot Metric 3D Prediction...	2023-07-20	Code
31	VA-DepthNet(SwinV1-L)	0.086	No	VA-DepthNet: A Variational Approach to Single Im...	2023-02-13	Code
32	iDisc	0.086	No	iDisc: Internal Discretization for Monocular Dep...	2023-04-13	Code
33	MIM-Swin-V2	0.0864	No	Analysis of NaN Divergence in Training Monocular...	2023-11-07	-
34	NDDepth	0.087	No	NDDepth: Normal-Distance Assisted Monocular Dept...	2023-09-19	Code
35	IEBins	0.087	No	IEBins: Iterative Elastic Bins for Monocular Dep...	2023-09-25	Code
36	URCDC-Depth	0.088	No	URCDC-Depth: Uncertainty Rectified Cross-Distill...	2023-02-16	Code
37	OrdinalEntropy	0.089	No	Improving Deep Regression with Ordinal Entropy	2023-01-21	Code
38	PixelFormer	0.09	No	Attention Attention Everywhere: Monocular Depth ...	2022-10-17	Code
39	LeReS	0.09	Yes	Learning to Recover 3D Scene Shape from a Single...	2020-12-17	Code
40	DINOv2 (ViT-g/14 frozen, w/ DPT decoder)	0.0907	Yes	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
41	DDP (step3)	0.094	No	DDP: Diffusion Model for Dense Visual Prediction	2023-03-30	Code
42	BinsFormer	0.094	No	BinsFormer: Revisiting Adaptive Bins for Monocul...	2022-04-03	Code
43	NeWCRFs	0.095	No	NeW CRFs: Neural Window Fully-connected CRFs for...	2022-03-03	Code
44	D-Net	0.095	No	-	-	Code
45	DepthFormer	0.096	No	DepthFormer: Exploiting Long-Range Correlation a...	2022-03-27	Code
46	GLPDepth	0.098	No	Global-Local Path Networks for Monocular Depth E...	2022-01-19	Code
47	LocalBins	0.098	No	LocalBins: Improving Depth Estimation by Learnin...	2022-03-28	Code
48	Depth-Map-Decomposition-HRWSI	0.098	Yes	Depth Map Decomposition for Monocular Depth Esti...	2022-08-23	Code
49	Depthformer	0.1	No	Depthformer : Multiscale Vision Transformer For ...	2022-07-10	Code
50	Depth-Map-Decomposition	0.1	No	Depth Map Decomposition for Monocular Depth Esti...	2022-08-23	Code
51	IronDepth	0.101	No	IronDepth: Iterative Refinement of Single-View D...	2022-10-07	Code
52	AdaBins	0.103	No	AdaBins: Depth Estimation using Adaptive Bins	2020-11-28	Code
53	P3Depth	0.104	No	P3Depth: Monocular Depth Estimation with a Piece...	2022-04-05	Code
54	CutDepth	0.104	Yes	CutDepth:Edge-aware Data Augmentation in Depth E...	2021-07-16	Code
55	LapDepth	0.105	No	-	-	Code
56	DPT-Hybrid	0.11	Yes	Vision Transformers for Dense Prediction	2021-03-24	Code
57	VNL	0.111	No	Enforcing geometric constraints of virtual norma...	2019-07-29	Code
58	Focal-WNet	0.116	No	-	-	Code
59	SC-DepthV2	0.138	No	Auto-Rectify Network for Unsupervised Indoor Dep...	2020-06-04	Code

#1HybridDepthSOTA
0.026
absolute relative error· 2024-07-26
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors Code
#2Distill Any Depth
0.043
absolute relative error· 2025-02-26
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator Code
#3UniK3D (FT, metric)
0.044
absolute relative error· 2025-03-20
UniK3D: Universal Camera Monocular 3D Estimation Code
#4UniDepthV2 (FT, metric)
0.046
absolute relative error· Augmentations· 2025-02-27
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler Code
#5PrimeDepth + Depth Anything
0.046
absolute relative error· 2024-09-13
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage Code
#6Metric3Dv2(L, FT)SOTA
0.047
absolute relative error· Augmentations· 2024-03-22
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation Code
#7DepthMaster
0.05
absolute relative error· Augmentations· 2025-01-05
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation Code
#8GRIN
0.051
absolute relative error· Augmentations· 2024-09-15
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
#9Marigold + E2E FT(zero-shot)
0.052
absolute relative error· 2024-09-17
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think Code
#10MarigoldSOTA
0.055
absolute relative error· Augmentations· 2023-12-04
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation Code
#11Depth Anything
0.056
absolute relative error· Augmentations· 2024-01-19
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Code
#12UniDepth (Zero-shot)
0.058
absolute relative error· Augmentations· 2024-03-27
UniDepth: Universal Monocular Metric Depth Estimation Code
#13PrimeDepth
0.058
absolute relative error· 2024-09-13
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage Code
#14ECoDepth
0.059
absolute relative error· 2024-03-27
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation Code
#15MetaPrompt-SD
0.061
absolute relative error· Augmentations· 2023-12-22
Harnessing Diffusion Models for Visual Perception with Meta Prompts Code
#16EVP
0.061
absolute relative error· 2023-12-13
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment Code
#17TADPSOTA
0.062
absolute relative error· Augmentations· 2023-09-29
Text-image Alignment for Diffusion-based Perception Code
#18FutureDepth
0.063
absolute relative error· 2024-03-19
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
#19MeSa
0.066
absolute relative error· 2023-10-06
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
#20PolyMaX(ConvNeXt-L)
0.067
absolute relative error· Augmentations· 2023-11-09
PolyMaX: General Dense Prediction with Mask Transformer Code
#21VPDSOTA
0.069
absolute relative error· 2023-03-03
Unleashing Text-to-Image Diffusion Models for Visual Perception Code
#22NVDS(DPT-L)
0.072
absolute relative error· Augmentations· 2023-07-17
NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation Code
#23DMD
0.072
absolute relative error· Augmentations· 2023-12-20
Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model
#24ScaleDepth-N
0.074
absolute relative error· 2024-07-11
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation Code
#25DepthGenSOTA
0.074
absolute relative error· Augmentations· 2023-02-28
Monocular Depth Estimation using Diffusion Models
#26ZoeD-M12-NSOTA
0.075
absolute relative error· Augmentations· 2023-02-23
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth Code
#27AiT-P(SwinV2-L)SOTA
0.076
absolute relative error· 2023-01-05
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token Code
#28Gaming for Depth (GfD)
0.08
absolute relative error· Augmentations
No paper
#29SwinV2-L 1K-MIMSOTA
0.083
absolute relative error· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#30Metric3D (ConvNeXt-Large, Zero-shot testing)
0.083
absolute relative error· Augmentations· 2023-07-20
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image Code
#31VA-DepthNet(SwinV1-L)
0.086
absolute relative error· 2023-02-13
VA-DepthNet: A Variational Approach to Single Image Depth Prediction Code
#32iDisc
0.086
absolute relative error· 2023-04-13
iDisc: Internal Discretization for Monocular Depth Estimation Code
#33MIM-Swin-V2
0.0864
absolute relative error· 2023-11-07
Analysis of NaN Divergence in Training Monocular Depth Estimation Model
#34NDDepth
0.087
absolute relative error· 2023-09-19
NDDepth: Normal-Distance Assisted Monocular Depth Estimation Code
#35IEBins
0.087
absolute relative error· 2023-09-25
IEBins: Iterative Elastic Bins for Monocular Depth Estimation Code
#36URCDC-Depth
0.088
absolute relative error· 2023-02-16
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation Code
#37OrdinalEntropy
0.089
absolute relative error· 2023-01-21
Improving Deep Regression with Ordinal Entropy Code
#38PixelFormer
0.09
absolute relative error· 2022-10-17
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention Code
#39LeReSSOTA
0.09
absolute relative error· Augmentations· 2020-12-17
Learning to Recover 3D Scene Shape from a Single Image Code
#40DINOv2 (ViT-g/14 frozen, w/ DPT decoder)
0.0907
absolute relative error· Augmentations· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#41DDP (step3)
0.094
absolute relative error· 2023-03-30
DDP: Diffusion Model for Dense Visual Prediction Code
#42BinsFormer
0.094
absolute relative error· 2022-04-03
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation Code
#43NeWCRFs
0.095
absolute relative error· 2022-03-03
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation Code
#44D-Net
0.095
absolute relative error
No paperCode
#45DepthFormer
0.096
absolute relative error· 2022-03-27
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation Code
#46GLPDepth
0.098
absolute relative error· 2022-01-19
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth Code
#47LocalBins
0.098
absolute relative error· 2022-03-28
LocalBins: Improving Depth Estimation by Learning Local Distributions Code
#48Depth-Map-Decomposition-HRWSI
0.098
absolute relative error· Augmentations· 2022-08-23
Depth Map Decomposition for Monocular Depth Estimation Code
#49Depthformer
0.1
absolute relative error· 2022-07-10
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion Code
#50Depth-Map-Decomposition
0.1
absolute relative error· 2022-08-23
Depth Map Decomposition for Monocular Depth Estimation Code
#51IronDepth
0.101
absolute relative error· 2022-10-07
IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty Code
#52AdaBinsSOTA
0.103
absolute relative error· 2020-11-28
AdaBins: Depth Estimation using Adaptive Bins Code
#53P3Depth
0.104
absolute relative error· 2022-04-05
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior Code
#54CutDepth
0.104
absolute relative error· Augmentations· 2021-07-16
CutDepth:Edge-aware Data Augmentation in Depth Estimation Code
#55LapDepth
0.105
absolute relative error
No paperCode
#56DPT-Hybrid
0.11
absolute relative error· Augmentations· 2021-03-24
Vision Transformers for Dense Prediction Code
#57VNLSOTA
0.111
absolute relative error· 2019-07-29
Enforcing geometric constraints of virtual normal for depth prediction Code
#58Focal-WNet
0.116
absolute relative error
No paperCode
#59SC-DepthV2
0.138
absolute relative error· 2020-06-04
Auto-Rectify Network for Unsupervised Indoor Depth Estimation Code