StyleGAN-XL (DINOv2)

Reported on 3 benchmarks across 1 task · 1 paper

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

Medical3 results

Image GenerationonFFHQ 256 x 256
FD· 2022-02-01
240.07
best: 592.26 (Projected-GAN (DINOv2))
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets arXiv:2202.00273
Image GenerationonFFHQ 256 x 256
Precision· 2022-02-01
0.77
best: 0.92 (LDM (DINOv2))
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets arXiv:2202.00273
Image GenerationonFFHQ 256 x 256
Recall· 2022-02-01
0.43
best: 0.76 (LDM (DINOv2))
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets arXiv:2202.00273