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/SPADE + SESAME

SPADE + SESAME

Reported on 12 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Computer Vision4 results

  • Image-to-Image TranslationonCityscapes Labels-to-Photo
    mIoU· 2020-04-10
    66
    best: 76.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image-to-Image TranslationonADE20K Labels-to-Photos
    mIoU· 2020-04-10
    49
    best: 54.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image-to-Image TranslationonCityscapes Labels-to-Photo
    FID· 2020-04-10
    54.2
    best: 38.2 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image-to-Image TranslationonADE20K Labels-to-Photos
    FID· 2020-04-10
    31.9
    best: 22.7 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977

Medical4 results

  • Image GenerationonCityscapes Labels-to-Photo
    mIoU· 2020-04-10
    66
    best: 76.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image GenerationonADE20K Labels-to-Photos
    mIoU· 2020-04-10
    49
    best: 54.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image GenerationonCityscapes Labels-to-Photo
    FID· 2020-04-10
    54.2
    best: 38.2 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • Image GenerationonADE20K Labels-to-Photos
    FID· 2020-04-10
    31.9
    best: 22.7 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977

Miscellaneous4 results

  • 1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
    mIoU· 2020-04-10
    66
    best: 76.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • 1 Image, 2*2 StitchingonADE20K Labels-to-Photos
    mIoU· 2020-04-10
    49
    best: 54.3 (DP-SIMS (ConvNext-L))
    SOTA
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • 1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
    FID· 2020-04-10
    54.2
    best: 38.2 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977
  • 1 Image, 2*2 StitchingonADE20K Labels-to-Photos
    FID· 2020-04-10
    31.9
    best: 22.7 (DP-SIMS (ConvNext-L))
    SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsarXiv:2004.04977