Powers of layers for image-to-image translation

We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoencoder architecture with fixed weights... (read more)

PDF Abstract ICLR 2021 PDF (under review) ICLR 2021 Abstract (under review)

Results from the Paper


 Ranked #1 on Image-to-Image Translation on horse2zebra (Frechet Inception Distance metric)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image-to-Image Translation horse2zebra PoL (CycleGAN) Frechet Inception Distance 53.0 # 1
Number of params 15.9M # 2
Image-to-Image Translation photo2vangogh PoL (CycleGAN) Frechet Inception Distance 152.7 # 2
Number of params 15.9M # 2
Image-to-Image Translation vangogh2photo PoL (CycleGAN) Frechet Inception Distance 134.4 # 1
Number of Params 15.9M # 2
Image-to-Image Translation zebra2horse PoL (CycleGAN) Frechet Inception Distance 112.3 # 2
Number of params 15.9M # 2

Methods used in the Paper