Image To Image Translation On Horse2Zebra
Metrics
Frechet Inception Distance
Number of params
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| CycleGAN | 89.7 | 28.2M | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks |
| PoL (CycleGAN) | 53.0 | 15.9M | Powers of layers for image-to-image translation |
| CycleGANAS | 38.06 | 8.751M | CycleGANAS: Differentiable Neural Architecture Search for CycleGAN |
| U-GAT-IT | - | - | U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation |
0 of 4 row(s) selected.