DRIT

Reported on 6 benchmarks across 3 tasks · 1 paper

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

Computer Vision2 results

Image-to-Image TranslationonCelebA-HQ
FID· 2018-08-02
52.1
best: 13.73 (StarGAN v2)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948
Image-to-Image TranslationonAFHQ
FID· 2018-08-02
95.6
best: 16.2 (StarGAN v2)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948

Medical2 results

Image GenerationonCelebA-HQ
FID· 2018-08-02
52.1
best: 4.86 (MAT)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948
Image GenerationonAFHQ
FID· 2018-08-02
95.6
best: 16.2 (StarGAN v2)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948

Miscellaneous2 results

1 Image, 2*2 StitchingonCelebA-HQ
FID· 2018-08-02
52.1
best: 13.73 (StarGAN v2)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948
1 Image, 2*2 StitchingonAFHQ
FID· 2018-08-02
95.6
best: 16.2 (StarGAN v2)
Diverse Image-to-Image Translation via Disentangled Representations arXiv:1808.00948