TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/HDNet

HDNet

Reported on 30 benchmarks across 10 tasks · 3 papers · 13 SOTA

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

Computer Vision16 results

  • 3D Multi-Person Pose Estimation (root-relative)onMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.6 (TDBU_Net)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 3D Human Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 3D Multi-Person Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • Image RestorationonKAIST
    PSNR· 2022-03-04
    34.97
    best: 40.69 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonKAIST
    SSIM· 2022-03-04
    0.943
    best: 0.978 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonCAVE
    PSNR· 2022-03-04
    34.97
    best: 40.69 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonCAVE
    SSIM· 2022-03-04
    0.943
    best: 0.978 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonReal HSI
    User Study Score· 2022-03-04
    11
    best: 15 (DAUHST-9stg)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonARAD-1K
    MRAE· 2022-03-04
    0.2048
    best: 0.3814 (HSCNN+)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonARAD-1K
    PSNR· 2022-03-04
    32.13
    best: 34.32 (MST++)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • Image RestorationonARAD-1K
    RMSE· 2022-03-04
    0.0317
    best: 0.0248 (MST++)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 3D Human Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 3D Multi-Person Pose Estimation (absolute)onMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 50.9 (POTR-3D)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 3D Multi-Person Pose EstimationonMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943

Audio10 results

  • 1 Image, 2*2 StitchionMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 10-shot image generationonKAIST
    PSNR· 2022-03-04
    34.97
    best: 40.69 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonKAIST
    SSIM· 2022-03-04
    0.943
    best: 0.978 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonCAVE
    PSNR· 2022-03-04
    34.97
    best: 40.69 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonCAVE
    SSIM· 2022-03-04
    0.943
    best: 0.978 (SSR)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonReal HSI
    User Study Score· 2022-03-04
    11
    best: 15 (DAUHST-9stg)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonARAD-1K
    MRAE· 2022-03-04
    0.2048
    best: 0.3814 (HSCNN+)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonARAD-1K
    PSNR· 2022-03-04
    32.13
    best: 34.32 (MST++)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 10-shot image generationonARAD-1K
    RMSE· 2022-03-04
    0.0317
    best: 0.0248 (MST++)
    HDNet: High-resolution Dual-domain Learning for Spectral Compressive ImagingarXiv:2203.02149
  • 1 Image, 2*2 StitchionMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943

Medical7 results

  • Image GenerationoniHarmony4
    MSE· 2022-11-16
    16.55
    best: 16.05 (PHNet)
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationoniHarmony4
    PSNR· 2022-11-16
    40.46
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationoniHarmony4
    fMSE· 2022-11-16
    179.49
    best: 178.11 (PHNet)
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationonHAdobe5k(1024$\times$1024)
    MSE· 2022-11-16
    13.24
    best: 10.94 (DucoNet)
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationonHAdobe5k(1024$\times$1024)
    PSNR· 2022-11-16
    41.56
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationonHAdobe5k(1024$\times$1024)
    SSIM· 2022-11-16
    0.9931
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639
  • Image GenerationonHAdobe5k(1024$\times$1024)
    fMSE· 2022-11-16
    102.53
    best: 80.69 (DucoNet)
    SOTA
    Hierarchical Dynamic Image HarmonizationarXiv:2211.08639

Methodology2 results

  • 3DonMuPoTS-3D
    3DPCK· 2020-07-17
    83.7
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    SOTA
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943
  • 3DonMuPoTS-3D
    3DPCK· 2020-07-17
    35.2
    best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
    HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationarXiv:2007.08943