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/MetaPrompt-SD

MetaPrompt-SD

Reported on 35 benchmarks across 6 tasks · 1 paper

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

Computer Vision14 results

Depth EstimationonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-12-22
0.976
best: 0.989 (UniK3D (FT, metric))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-12-22
0.997
best: 1 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-12-22
0.999
best: 1 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2023-12-22
0.223
best: 0.013 (Defocus/DepthNet (Normalized))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonNYU-Depth V2
absolute relative error· uses extra data· 2023-12-22
0.061
best: 0.026 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonNYU-Depth V2
log 10· uses extra data· 2023-12-22
0.027
best: 0.059 (SC-DepthV2)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
Delta < 1.25· uses extra data· 2023-12-22
0.981
best: 0.99 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2023-12-22
0.998
best: 0.999 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2023-12-22
1
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
RMSE· uses extra data· 2023-12-22
1.928
best: 1.394 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
RMSE log· uses extra data· 2023-12-22
0.071
best: 0.048 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
Sq Rel· uses extra data· 2023-12-22
0.125
best: 0.224 (SfM-Revisited)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Depth EstimationonKITTI Eigen split
absolute relative error· uses extra data· 2023-12-22
0.047
best: 0.029 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Pose EstimationonCOCO (Common Objects in Context)
AP· 2023-12-22
79
best: 79.5 (OmniPose (WASPv2))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733

Methodology14 results

3DonCOCO (Common Objects in Context)
AP· 2023-12-22
79
best: 79.5 (OmniPose (WASPv2))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-12-22
0.976
best: 0.989 (UniK3D (FT, metric))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-12-22
0.997
best: 1 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-12-22
0.999
best: 1 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
RMSE· uses extra data· 2023-12-22
0.223
best: 0.013 (Defocus/DepthNet (Normalized))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
absolute relative error· uses extra data· 2023-12-22
0.061
best: 0.026 (HybridDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonNYU-Depth V2
log 10· uses extra data· 2023-12-22
0.027
best: 0.059 (SC-DepthV2)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
Delta < 1.25· uses extra data· 2023-12-22
0.981
best: 0.99 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2023-12-22
0.998
best: 0.999 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2023-12-22
1
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
RMSE· uses extra data· 2023-12-22
1.928
best: 1.394 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
RMSE log· uses extra data· 2023-12-22
0.071
best: 0.048 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
Sq Rel· uses extra data· 2023-12-22
0.125
best: 0.224 (SfM-Revisited)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
3DonKITTI Eigen split
absolute relative error· uses extra data· 2023-12-22
0.047
best: 0.029 (SPIDepth)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733

Audio4 results

10-shot image generationonCityscapes test
Mean IoU (class)· 2023-12-22
86.2
best: 86.4 (VLTSeg)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
10-shot image generationonCityscapes val
mIoU· uses extra data· 2023-12-22
87.1
best: 90.3 (EfficientPS (Cityscapes-fine))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
10-shot image generationonADE20K
Validation mIoU· 2023-12-22
56.8
best: 63.6 (ViT-P (InternImage-H))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
AP· 2023-12-22
79
best: 79.5 (OmniPose (WASPv2))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733

Medical3 results

Semantic SegmentationonCityscapes test
Mean IoU (class)· 2023-12-22
86.2
best: 86.4 (VLTSeg)
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2023-12-22
87.1
best: 90.3 (EfficientPS (Cityscapes-fine))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733
Semantic SegmentationonADE20K
Validation mIoU· 2023-12-22
56.8
best: 63.6 (ViT-P (InternImage-H))
Harnessing Diffusion Models for Visual Perception with Meta Prompts arXiv:2312.14733