Mo-VQGAN (16x16x4)

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· 2022-09-19
1.12
best: 0.49 (MGVQ (16x16x8))
SOTA
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation arXiv:2209.09002
Image ReconstructiononImageNet
LPIPS· 2022-09-19
0.113
best: 0.066 (OptVQ (16x16x8))
SOTA
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation arXiv:2209.09002
Image ReconstructiononImageNet
PSNR· 2022-09-19
22.42
best: 27.57 (OptVQ (16x16x8))
SOTA
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation arXiv:2209.09002
Image ReconstructiononImageNet
SSIM· 2022-09-19
0.673
best: 0.787 (MGVQ (16x16x8))
SOTA
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation arXiv:2209.09002