HyperAI超神経

プラットフォーム

Fundus To Angiography Generation On Fundus

評価指標

FID

Kernel Inception Distance

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

			Paper Title
pix2pix	48.6	-	Image-to-Image Translation with Conditional Adversarial Networks
Attention2Angio w/o Perceptual Loss + Feature Matching Loss	47.5	0.00595	Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
pix2pixHD	42.8	0.00258	High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Fundus2Angio	30.3	0.00184	Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
StarGAN-v2	27.7	0.00118	StarGAN v2: Diverse Image Synthesis for Multiple Domains
Attention2Angio	24.6	0.00087	Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
U-GAT-IT	24.5	0.00131	U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
Attention2Angio w/o Perceptual Loss	20.7	0.00392	Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
VTGAN	17.3	0.00053	VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers

0 of 9 row(s) selected.