Surface Normals Estimation on NYU Depth v2

Metric: Mean Angle Error (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Mean Angle Error▲	Extra Data	Paper	Date↕	Code
1	Metric3Dv2(L, FT)	12	Yes	Metric3Dv2: A Versatile Monocular Geometric Foun...	2024-03-22	Code
2	PolyMaX(ConvNeXt-L)	13.09	No	PolyMaX: General Dense Prediction with Mask Tran...	2023-11-09	Code
3	iDisc	14.6	No	iDisc: Internal Discretization for Monocular Dep...	2023-04-13	Code
4	Bae et al.	14.9	No	Estimating and Exploiting the Aleatoric Uncertai...	2021-09-20	Code
5	Marigold + E2E FT(zero-shot)	16.2	No	Fine-Tuning Image-Conditional Diffusion Models i...	2024-09-17	Code
6	Floors are Flat	19.7	No	Floors are Flat: Leveraging Semantics for Real-T...	2019-06-16	Code

#1Metric3Dv2(L, FT)SOTA
12
Mean Angle Error· Extra Data· 2024-03-22
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation Code
#2PolyMaX(ConvNeXt-L)SOTA
13.09
Mean Angle Error· 2023-11-09
PolyMaX: General Dense Prediction with Mask Transformer Code
#3iDiscSOTA
14.6
Mean Angle Error· 2023-04-13
iDisc: Internal Discretization for Monocular Depth Estimation Code
#4Bae et al.SOTA
14.9
Mean Angle Error· 2021-09-20
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation Code
#5Marigold + E2E FT(zero-shot)
16.2
Mean Angle Error· 2024-09-17
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think Code
#6Floors are FlatSOTA
19.7
Mean Angle Error· 2019-06-16
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction Code