Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PolyMaX(ConvNeXt-L)

PolyMaX(ConvNeXt-L)

Reported on 17 benchmarks across 3 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision11 results

Surface Normals EstimationonNYU Depth v2
% < 11.25· 2023-11-09
65.66
best: 68.8 (Metric3Dv2(L, FT))
SOTA
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Surface Normals EstimationonNYU Depth v2
% < 22.5· 2023-11-09
82.28
best: 84.9 (Metric3Dv2(L, FT))
SOTA
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Surface Normals EstimationonNYU Depth v2
% < 30· 2023-11-09
87.83
best: 89.8 (Metric3Dv2(L, FT))
SOTA
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Surface Normals EstimationonNYU Depth v2
Mean Angle Error· 2023-11-09
13.09
best: 12 (Metric3Dv2(L, FT))
SOTA
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-11-09
0.969
best: 0.989 (UniK3D (FT, metric))
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-11-09
0.9958
best: 1 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-11-09
0.999
best: 1 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2023-11-09
0.25
best: 0.013 (Defocus/DepthNet (Normalized))
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
absolute relative error· uses extra data· 2023-11-09
0.067
best: 0.026 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Depth EstimationonNYU-Depth V2
log 10· uses extra data· 2023-11-09
0.029
best: 0.059 (SC-DepthV2)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
Surface Normals EstimationonNYU Depth v2
RMSE· 2023-11-09
20.4
best: 19.2 (Metric3Dv2(L, FT))
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770

Methodology6 results

3DonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-11-09
0.969
best: 0.989 (UniK3D (FT, metric))
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
3DonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-11-09
0.9958
best: 1 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
3DonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-11-09
0.999
best: 1 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
3DonNYU-Depth V2
RMSE· uses extra data· 2023-11-09
0.25
best: 0.013 (Defocus/DepthNet (Normalized))
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
3DonNYU-Depth V2
absolute relative error· uses extra data· 2023-11-09
0.067
best: 0.026 (HybridDepth)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770
3DonNYU-Depth V2
log 10· uses extra data· 2023-11-09
0.029
best: 0.059 (SC-DepthV2)
PolyMaX: General Dense Prediction with Mask Transformer arXiv:2311.05770