Taming-VQGAN (16x16)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Medical4 results

Image ReconstructiononImageNet
FID· 2020-12-17
3.64
best: 0.49 (MGVQ (16x16x8))
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841
Image ReconstructiononImageNet
LPIPS· 2020-12-17
0.177
best: 0.066 (OptVQ (16x16x8))
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841
Image ReconstructiononImageNet
PSNR· 2020-12-17
19.93
best: 27.57 (OptVQ (16x16x8))
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841
Image ReconstructiononImageNet
SSIM· 2020-12-17
0.542
best: 0.787 (MGVQ (16x16x8))
SOTA
Taming Transformers for High-Resolution Image Synthesis arXiv:2012.09841