FID-10k-training-steps: 10.8309Clean-FID (70k): 2.98
Papers with Code · CC BY-SA 4.0
Image Generation
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
<span style="color:grey; opacity: 0.6">( Image credit: StyleGAN )</span>
논문
FID: 14.5
nats: 79.20
nats: 88.33
FID: 4.42Clean-FID (70k): 4.77
nats: 77.87
nats: 76.93
FID: 1.51
nats: 79.09
clean-KID: 0.38 ± .02clean-FID: 2.35 ± .02FID: 2.25
FID: 4.16
FID: 6.37
FID: 13.95
nats: 84.68
nats: 85.10
bits/dimension: 0.143nats: 77.58
nats: 86.64
Clean-FID (70k): 6.51
FID: 11.46
FID: 2.17
RMSE Signature: 33306RMSE log-signature: 26622MAE Signature: 25578MAE log-signature: 20359
FID: 5.07
clean-KID: 0.44 ± .01clean-FID: 3.00 ± .01FID: 3.05