Image To Image Translation On Cityscapes 1
评估指标
Class IOU
Per-class Accuracy
Per-pixel Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||||
|---|---|---|---|---|---|
| pix2pix | 0.32 | 40.0% | 85.0% | Image-to-Image Translation with Conditional Adversarial Networks | |
| CycleGAN | 0.16 | 22% | 58% | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks | |
| CoGAN | 0.08 | 11% | 45% | Coupled Generative Adversarial Networks | |
| SimGAN | 0.07 | 11% | 47% | Learning from Simulated and Unsupervised Images through Adversarial Training | |
| BiGAN | 0.07 | 13% | 41% | Adversarially Learned Inference |
0 of 5 row(s) selected.