Image Reconstruction on ImageNet 50k 2012 (val)
0.59rFIDLlamaGen
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LlamaGenratio=8, dim=8, size=16384, training_data=ImageNet, resolution=256x2562024.06 | 0.59 | 24.45 | 0.813 | |
| SDXL-VAEratio=8, dim=4, training_data=Unknown, resolution=256x2562024.06 | 0.68 | 26.04 | 0.834 | |
| SD-VAEratio=8, dim=4, training_data=Unknown, resolution=256x2562024.06 | 0.74 | 25.68 | 0.82 | |
| OAI-Decoderratio=8, dim=4, training_data=Unknown, resolution=256x2562024.06 | 0.81 | 24.43 | 0.786 | |
| VQGANratio=8, dim=4, size=16384, training_data=OpenImage, resolution=256x2562024.06 | 1.19 | 23.38 | 0.762 | |
| ViT-VQGANratio=8, dim=32, size=8192, training_data=ImageNet, resolution=256x2562024.06 | 1.28 | — | — | |
| VQGANratio=8, dim=4, size=256, training_data=OpenImage, resolution=256x2562024.06 | 1.44 | 22.63 | 0.737 | |
| LlamaGenratio=16, dim=8, size=16384, training_data=ImageNet, resolution=256x2562024.06 | 2.19 | 20.79 | 0.675 | |
| MaskGITratio=16, dim=256, size=1024, training_data=ImageNet, resolution=256x2562024.06 | 2.28 | — | — | |
| VQGANratio=16, dim=256, size=16384, training_data=ImageNet, resolution=256x2562024.06 | 4.99 | 20 | 0.629 | |
| VQGANratio=16, dim=256, size=1024, training_data=ImageNet, resolution=256x2562024.06 | 8.3 | 19.51 | 0.614 |