Depth Estimation on NYU-Depth V2

Metric: log 10 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	log 10▼	Extra Data	Paper	Date↕	Code
1	SC-DepthV2	0.059	No	Auto-Rectify Network for Unsupervised Indoor Dep...	2020-06-04	Code
2	VNL	0.048	No	Enforcing geometric constraints of virtual norma...	2019-07-29	Code
3	Focal-WNet	0.048	No	-	-	Code
4	LapDepth	0.045	No	-	-	Code
5	DPT-Hybrid	0.045	Yes	Vision Transformers for Dense Prediction	2021-03-24	Code
6	AdaBins	0.044	No	AdaBins: Depth Estimation using Adaptive Bins	2020-11-28	Code
7	CutDepth	0.044	Yes	CutDepth:Edge-aware Data Augmentation in Depth E...	2021-07-16	Code
8	Depth-Map-Decomposition	0.043	No	Depth Map Decomposition for Monocular Depth Esti...	2022-08-23	Code
9	IronDepth	0.043	No	IronDepth: Iterative Refinement of Single-View D...	2022-10-07	Code
10	P3Depth	0.043	No	P3Depth: Monocular Depth Estimation with a Piece...	2022-04-05	Code
11	GLPDepth	0.042	No	Global-Local Path Networks for Monocular Depth E...	2022-01-19	Code
12	LocalBins	0.042	No	LocalBins: Improving Depth Estimation by Learnin...	2022-03-28	Code
13	Depth-Map-Decomposition-HRWSI	0.042	Yes	Depth Map Decomposition for Monocular Depth Esti...	2022-08-23	Code
14	Depthformer	0.042	No	Depthformer : Multiscale Vision Transformer For ...	2022-07-10	Code
15	NeWCRFs	0.041	No	NeW CRFs: Neural Window Fully-connected CRFs for...	2022-03-03	Code
16	D-Net	0.041	No	-	-	Code
17	DepthFormer	0.041	No	DepthFormer: Exploiting Long-Range Correlation a...	2022-03-27	Code
18	DDP (step3)	0.04	No	DDP: Diffusion Model for Dense Visual Prediction	2023-03-30	Code
19	BinsFormer	0.04	No	BinsFormer: Revisiting Adaptive Bins for Monocul...	2022-04-03	Code
20	OrdinalEntropy	0.039	No	Improving Deep Regression with Ordinal Entropy	2023-01-21	Code
21	PixelFormer	0.039	No	Attention Attention Everywhere: Monocular Depth ...	2022-10-17	Code
22	NDDepth	0.038	No	NDDepth: Normal-Distance Assisted Monocular Dept...	2023-09-19	Code
23	IEBins	0.038	No	IEBins: Iterative Elastic Bins for Monocular Dep...	2023-09-25	Code
24	URCDC-Depth	0.038	No	URCDC-Depth: Uncertainty Rectified Cross-Distill...	2023-02-16	Code
25	DINOv2 (ViT-g/14 frozen, w/ DPT decoder)	0.0371	Yes	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
26	VA-DepthNet(SwinV1-L)	0.037	No	VA-DepthNet: A Variational Approach to Single Im...	2023-02-13	Code
27	MIM-Swin-V2	0.0365	No	Analysis of NaN Divergence in Training Monocular...	2023-11-07	-
28	SwinV2-L 1K-MIM	0.035	No	Revealing the Dark Secrets of Masked Image Model...	2022-05-26	Code
29	Metric3D (ConvNeXt-Large, Zero-shot testing)	0.035	Yes	Metric3D: Towards Zero-shot Metric 3D Prediction...	2023-07-20	Code
30	AiT-P(SwinV2-L)	0.033	No	All in Tokens: Unifying Output Space of Visual T...	2023-01-05	Code
31	Gaming for Depth (GfD)	0.033	Yes	-	-	-
32	ScaleDepth-N	0.032	No	ScaleDepth: Decomposing Metric Depth Estimation ...	2024-07-11	Code
33	DepthGen	0.032	Yes	Monocular Depth Estimation using Diffusion Models	2023-02-28	-
34	ZoeD-M12-N	0.032	Yes	ZoeDepth: Zero-shot Transfer by Combining Relati...	2023-02-23	Code
35	NVDS(DPT-L)	0.031	Yes	NVDS+: Towards Efficient and Versatile Neural St...	2023-07-17	Code
36	DMD	0.031	Yes	Zero-Shot Metric Depth with a Field-of-View Cond...	2023-12-20	-
37	VPD	0.03	No	Unleashing Text-to-Image Diffusion Models for Vi...	2023-03-03	Code
38	MeSa	0.029	No	MeSa: Masked, Geometric, and Supervised Pre-trai...	2023-10-06	-
39	PolyMaX(ConvNeXt-L)	0.029	Yes	PolyMaX: General Dense Prediction with Mask Tran...	2023-11-09	Code
40	MetaPrompt-SD	0.027	Yes	Harnessing Diffusion Models for Visual Perceptio...	2023-12-22	Code
41	EVP	0.027	No	EVP: Enhanced Visual Perception using Inverse Mu...	2023-12-13	Code
42	TADP	0.027	Yes	Text-image Alignment for Diffusion-based Percept...	2023-09-29	Code
43	FutureDepth	0.027	No	FutureDepth: Learning to Predict the Future Impr...	2024-03-19	-
44	ECoDepth	0.026	No	ECoDepth: Effective Conditioning of Diffusion Mo...	2024-03-27	Code
45	Marigold	0.024	Yes	Repurposing Diffusion-Based Image Generators for...	2023-12-04	Code
46	Depth Anything	0.024	Yes	Depth Anything: Unleashing the Power of Large-Sc...	2024-01-19	Code
47	UniDepth (Zero-shot)	0.024	Yes	UniDepth: Universal Monocular Metric Depth Estim...	2024-03-27	Code
48	UniDepthV2 (FT, metric)	0.02	Yes	UniDepthV2: Universal Monocular Metric Depth Est...	2025-02-27	Code
49	Metric3Dv2(L, FT)	0.02	Yes	Metric3Dv2: A Versatile Monocular Geometric Foun...	2024-03-22	Code
50	UniK3D (FT, metric)	0.019	No	UniK3D: Universal Camera Monocular 3D Estimation	2025-03-20	Code

#1SC-DepthV2SOTA
0.059
log 10· 2020-06-04
Auto-Rectify Network for Unsupervised Indoor Depth Estimation Code
#2VNLSOTA
0.048
log 10· 2019-07-29
Enforcing geometric constraints of virtual normal for depth prediction Code
#3Focal-WNet
0.048
log 10
No paperCode
#4LapDepth
0.045
log 10
No paperCode
#5DPT-Hybrid
0.045
log 10· Extra Data· 2021-03-24
Vision Transformers for Dense Prediction Code
#6AdaBins
0.044
log 10· 2020-11-28
AdaBins: Depth Estimation using Adaptive Bins Code
#7CutDepth
0.044
log 10· Extra Data· 2021-07-16
CutDepth:Edge-aware Data Augmentation in Depth Estimation Code
#8Depth-Map-Decomposition
0.043
log 10· 2022-08-23
Depth Map Decomposition for Monocular Depth Estimation Code
#9IronDepth
0.043
log 10· 2022-10-07
IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty Code
#10P3Depth
0.043
log 10· 2022-04-05
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior Code
#11GLPDepth
0.042
log 10· 2022-01-19
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth Code
#12LocalBins
0.042
log 10· 2022-03-28
LocalBins: Improving Depth Estimation by Learning Local Distributions Code
#13Depth-Map-Decomposition-HRWSI
0.042
log 10· Extra Data· 2022-08-23
Depth Map Decomposition for Monocular Depth Estimation Code
#14Depthformer
0.042
log 10· 2022-07-10
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion Code
#15NeWCRFs
0.041
log 10· 2022-03-03
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation Code
#16D-Net
0.041
log 10
No paperCode
#17DepthFormer
0.041
log 10· 2022-03-27
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation Code
#18DDP (step3)
0.04
log 10· 2023-03-30
DDP: Diffusion Model for Dense Visual Prediction Code
#19BinsFormer
0.04
log 10· 2022-04-03
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation Code
#20OrdinalEntropy
0.039
log 10· 2023-01-21
Improving Deep Regression with Ordinal Entropy Code
#21PixelFormer
0.039
log 10· 2022-10-17
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention Code
#22NDDepth
0.038
log 10· 2023-09-19
NDDepth: Normal-Distance Assisted Monocular Depth Estimation Code
#23IEBins
0.038
log 10· 2023-09-25
IEBins: Iterative Elastic Bins for Monocular Depth Estimation Code
#24URCDC-Depth
0.038
log 10· 2023-02-16
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation Code
#25DINOv2 (ViT-g/14 frozen, w/ DPT decoder)
0.0371
log 10· Extra Data· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#26VA-DepthNet(SwinV1-L)
0.037
log 10· 2023-02-13
VA-DepthNet: A Variational Approach to Single Image Depth Prediction Code
#27MIM-Swin-V2
0.0365
log 10· 2023-11-07
Analysis of NaN Divergence in Training Monocular Depth Estimation Model
#28SwinV2-L 1K-MIM
0.035
log 10· 2022-05-26
Revealing the Dark Secrets of Masked Image Modeling Code
#29Metric3D (ConvNeXt-Large, Zero-shot testing)
0.035
log 10· Extra Data· 2023-07-20
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image Code
#30AiT-P(SwinV2-L)
0.033
log 10· 2023-01-05
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token Code
#31Gaming for Depth (GfD)
0.033
log 10· Extra Data
No paper
#32ScaleDepth-N
0.032
log 10· 2024-07-11
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation Code
#33DepthGen
0.032
log 10· Extra Data· 2023-02-28
Monocular Depth Estimation using Diffusion Models
#34ZoeD-M12-N
0.032
log 10· Extra Data· 2023-02-23
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth Code
#35NVDS(DPT-L)
0.031
log 10· Extra Data· 2023-07-17
NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation Code
#36DMD
0.031
log 10· Extra Data· 2023-12-20
Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model
#37VPD
0.03
log 10· 2023-03-03
Unleashing Text-to-Image Diffusion Models for Visual Perception Code
#38MeSa
0.029
log 10· 2023-10-06
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
#39PolyMaX(ConvNeXt-L)
0.029
log 10· Extra Data· 2023-11-09
PolyMaX: General Dense Prediction with Mask Transformer Code
#40MetaPrompt-SD
0.027
log 10· Extra Data· 2023-12-22
Harnessing Diffusion Models for Visual Perception with Meta Prompts Code
#41EVP
0.027
log 10· 2023-12-13
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment Code
#42TADP
0.027
log 10· Extra Data· 2023-09-29
Text-image Alignment for Diffusion-based Perception Code
#43FutureDepth
0.027
log 10· 2024-03-19
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
#44ECoDepth
0.026
log 10· 2024-03-27
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation Code
#45Marigold
0.024
log 10· Extra Data· 2023-12-04
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation Code
#46Depth Anything
0.024
log 10· Extra Data· 2024-01-19
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Code
#47UniDepth (Zero-shot)
0.024
log 10· Extra Data· 2024-03-27
UniDepth: Universal Monocular Metric Depth Estimation Code
#48UniDepthV2 (FT, metric)
0.02
log 10· Extra Data· 2025-02-27
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler Code
#49Metric3Dv2(L, FT)
0.02
log 10· Extra Data· 2024-03-22
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation Code
#50UniK3D (FT, metric)
0.019
log 10· 2025-03-20
UniK3D: Universal Camera Monocular 3D Estimation Code