SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects

Benchmark Model Rank Results
image-to-image-translation-on-ade20k-labels-to-photosSPADE + SESAME#3mIoU: 49Accuracy: 85.5%FID: 31.9
image-to-image-translation-on-cityscapes-labels-to-photoSPADE + SESAME#3mIoU: 66FID: 54.2Per-pixel Accuracy: 82.5%