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/PixelFormer

PixelFormer

Reported on 26 benchmarks across 2 tasks · 1 paper

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

Computer Vision13 results

Depth EstimationonNYU-Depth V2
Delta < 1.25· 2022-10-17
0.929
best: 0.989 (UniK3D (FT, metric))
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· 2022-10-17
0.991
best: 1 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· 2022-10-17
0.998
best: 1 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonNYU-Depth V2
RMSE· 2022-10-17
0.322
best: 0.013 (Defocus/DepthNet (Normalized))
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonNYU-Depth V2
absolute relative error· 2022-10-17
0.09
best: 0.026 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonNYU-Depth V2
log 10· 2022-10-17
0.039
best: 0.059 (SC-DepthV2)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
Delta < 1.25· uses extra data· 2022-10-17
0.976
best: 0.99 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2022-10-17
0.997
best: 0.999 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2022-10-17
0.999
best: 1 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
RMSE· uses extra data· 2022-10-17
2.081
best: 1.394 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
RMSE log· uses extra data· 2022-10-17
0.077
best: 0.048 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
Sq Rel· uses extra data· 2022-10-17
0.149
best: 0.224 (SfM-Revisited)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
Depth EstimationonKITTI Eigen split
absolute relative error· uses extra data· 2022-10-17
0.051
best: 0.029 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071

Methodology13 results

3DonNYU-Depth V2
Delta < 1.25· 2022-10-17
0.929
best: 0.989 (UniK3D (FT, metric))
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonNYU-Depth V2
Delta < 1.25^2· 2022-10-17
0.991
best: 1 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonNYU-Depth V2
Delta < 1.25^3· 2022-10-17
0.998
best: 1 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonNYU-Depth V2
RMSE· 2022-10-17
0.322
best: 0.013 (Defocus/DepthNet (Normalized))
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonNYU-Depth V2
absolute relative error· 2022-10-17
0.09
best: 0.026 (HybridDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonNYU-Depth V2
log 10· 2022-10-17
0.039
best: 0.059 (SC-DepthV2)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
Delta < 1.25· uses extra data· 2022-10-17
0.976
best: 0.99 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2022-10-17
0.997
best: 0.999 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2022-10-17
0.999
best: 1 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
RMSE· uses extra data· 2022-10-17
2.081
best: 1.394 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
RMSE log· uses extra data· 2022-10-17
0.077
best: 0.048 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
Sq Rel· uses extra data· 2022-10-17
0.149
best: 0.224 (SfM-Revisited)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071
3DonKITTI Eigen split
absolute relative error· uses extra data· 2022-10-17
0.051
best: 0.029 (SPIDepth)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention arXiv:2210.09071