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/VQGAN+Transformer

VQGAN+Transformer

Reported on 8 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Medical4 results

  • Image GenerationonCelebA-HQ 256x256
    FID· 2020-12-17
    10.2
    best: 3.15 (RDM)
    SOTA
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841
  • Image GenerationonFFHQ 256 x 256
    FID· 2020-12-17
    9.6
    best: 1.68 (StyleSAN-XL)
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841
  • Image GenerationonCOCO-Stuff Labels-to-Photos
    FID· 2020-12-17
    22.4
    best: 13.3 (DP-SIMS (ConvNext-XL))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841
  • Image GenerationonADE20K Labels-to-Photos
    FID· 2020-12-17
    35.5
    best: 22.7 (DP-SIMS (ConvNext-L))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841

Computer Vision2 results

  • Image-to-Image TranslationonCOCO-Stuff Labels-to-Photos
    FID· 2020-12-17
    22.4
    best: 13.3 (DP-SIMS (ConvNext-XL))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841
  • Image-to-Image TranslationonADE20K Labels-to-Photos
    FID· 2020-12-17
    35.5
    best: 22.7 (DP-SIMS (ConvNext-L))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841

Miscellaneous2 results

  • 1 Image, 2*2 StitchingonCOCO-Stuff Labels-to-Photos
    FID· 2020-12-17
    22.4
    best: 13.3 (DP-SIMS (ConvNext-XL))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841
  • 1 Image, 2*2 StitchingonADE20K Labels-to-Photos
    FID· 2020-12-17
    35.5
    best: 22.7 (DP-SIMS (ConvNext-L))
    Taming Transformers for High-Resolution Image SynthesisarXiv:2012.09841