High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Open paper
Benchmark Model Rank Results
fundus-to-angiography-generation-on-fundus-fluorescein-angiogram-photographspix2pixHD#6FID: 42.8Kernel Inception Distance: 0.00258
image-to-image-translation-on-ade20k-labels-to-photospix2pixHD#7mIoU: 20.3Accuracy: 69.2%FID: 81.8
image-to-image-translation-on-ade20k-outdoor-labels-to-photospix2pixHD#4mIoU: 17.4Accuracy: 71.6%FID: 97.8
image-to-image-translation-on-cityscapes-labels-to-photopix2pixHD#7mIoU: 58.3FID: 95Per-pixel Accuracy: 81.4%
image-to-image-translation-on-coco-stuff-labels-to-photospix2pixHD#9FID: 111.5Accuracy: 45.8%mIoU: 14.6
sketch-to-image-translation-on-coco-stuffPix2PixHD#2FID: 38.7FID-C: 27.1

Rank counts only results with a code link.