Surface Normals Estimation on NYU Depth v2

Metric: RMSE (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	RMSE▲	Extra Data	Paper	Date↕	Code
1	Metric3Dv2(L, FT)	19.2	Yes	Metric3Dv2: A Versatile Monocular Geometric Foun...	2024-03-22	Code
2	Floors are Flat	19.3	No	Floors are Flat: Leveraging Semantics for Real-T...	2019-06-16	Code
3	PolyMaX(ConvNeXt-L)	20.4	No	PolyMaX: General Dense Prediction with Mask Tran...	2023-11-09	Code
4	iDisc	22.8	No	iDisc: Internal Discretization for Monocular Dep...	2023-04-13	Code
5	Bae et al.	23.5	No	Estimating and Exploiting the Aleatoric Uncertai...	2021-09-20	Code

#1Metric3Dv2(L, FT)SOTA
19.2
RMSE· Extra Data· 2024-03-22
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation Code
#2Floors are FlatSOTA
19.3
RMSE· 2019-06-16
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction Code
#3PolyMaX(ConvNeXt-L)
20.4
RMSE· 2023-11-09
PolyMaX: General Dense Prediction with Mask Transformer Code
#4iDisc
22.8
RMSE· 2023-04-13
iDisc: Internal Discretization for Monocular Depth Estimation Code
#5Bae et al.
23.5
RMSE· 2021-09-20
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation Code