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/PIFu

PIFu

Reported on 20 benchmarks across 4 tasks · 1 paper · 18 SOTA

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

Computer Vision20 results

  • ReconstructiononCustomHumans
    Chamfer Distance P-to-S· uses extra data· 2019-05-13
    2.209
    best: 1.871 (SiTH)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • ReconstructiononCustomHumans
    Chamfer Distance S-to-P· uses extra data· 2019-05-13
    2.582
    best: 2.045 (SiTH)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • ReconstructiononCustomHumans
    Normal Consistency· uses extra data· 2019-05-13
    0.805
    best: 0.826 (SiTH)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • ReconstructiononCustomHumans
    f-Score· uses extra data· 2019-05-13
    34.881
    best: 39.076 (PIFuHD)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononRenderPeople
    Chamfer (cm)· uses extra data· 2019-05-13
    1.5
    best: 0.567 (PIFu (3 views))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononRenderPeople
    Point-to-surface distance (cm)· uses extra data· 2019-05-13
    1.52
    best: 2 (ali)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononBUFF
    Chamfer (cm)· 2019-05-13
    1.14
    best: 0.61 (ARCH++)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononBUFF
    Point-to-surface distance (cm)· 2019-05-13
    1.15
    best: 1.63 (ML-PIFu (alternate))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononBUFF
    Surface normal consistency· 2019-05-13
    0.0928
    best: 0.22 (ML-PIFu (end-to-end))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononRenderPeople
    Chamfer (cm)· uses extra data· 2019-05-13
    1.5
    best: 0.567 (PIFu (3 views))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononRenderPeople
    Point-to-surface distance (cm)· uses extra data· 2019-05-13
    1.52
    best: 2 (ali)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononBUFF
    Chamfer (cm)· 2019-05-13
    1.14
    best: 0.61 (ARCH++)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononBUFF
    Point-to-surface distance (cm)· 2019-05-13
    1.15
    best: 1.63 (ML-PIFu (alternate))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononBUFF
    Surface normal consistency· 2019-05-13
    0.0928
    best: 0.22 (ML-PIFu (end-to-end))
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Lifelike 3D Human GenerationonTHuman2.0 Dataset
    CLIP Similarity· 2019-05-13
    0.8501
    best: 0.9235 (Human-VDM)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Lifelike 3D Human GenerationonTHuman2.0 Dataset
    LPIPS· 2019-05-13
    0.1615
    best: 0.0957 (Human-VDM)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Lifelike 3D Human GenerationonTHuman2.0 Dataset
    PSNR· 2019-05-13
    15.0248
    best: 20.068 (Human-VDM)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Lifelike 3D Human GenerationonTHuman2.0 Dataset
    SSIM· 2019-05-13
    0.8884
    best: 0.9228 (Human-VDM)
    SOTA
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • Object ReconstructiononRenderPeople
    Surface normal consistency· uses extra data· 2019-05-13
    0.084
    best: 0.2 (ali)
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172
  • 3D Object ReconstructiononRenderPeople
    Surface normal consistency· uses extra data· 2019-05-13
    0.084
    best: 0.2 (ali)
    PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationarXiv:1905.05172