TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image-to-Image Translation	Aerial-to-Map	cGAN	Per-pixel Accuracy	70.0%	# 1
Image-to-Image Translation	Aerial-to-Map	cGAN	Per-class Accuracy	46.0%	# 1
Image-to-Image Translation	Aerial-to-Map	cGAN	Class IOU	0.26	# 1
Facial Expression Translation	AR Face	Enc.-Decoder	AMT	0.1	# 3
Facial Expression Translation	AR Face	Enc.-Decoder	PSNR	12.6660	# 3
Nuclear Segmentation	Cell17	Pix2Pix	F1-score	0.6208	# 4
Nuclear Segmentation	Cell17	Pix2Pix	Dice	0.6351	# 3
Nuclear Segmentation	Cell17	Pix2Pix	Hausdorff	19.1441	# 3
Image-to-Image Translation	Cityscapes Labels-to-Photo	pix2pix	Class IOU	0.18	# 1
Image-to-Image Translation	Cityscapes Labels-to-Photo	pix2pix	Per-class Accuracy	25.0	# 1
Image-to-Image Translation	Cityscapes Labels-to-Photo	pix2pix	Per-pixel Accuracy	71.0	# 8
Image-to-Image Translation	Cityscapes Labels-to-Photo	pix2pix	LPIPS	0	# 4
Image-to-Image Translation	Cityscapes Photo-to-Labels	pix2pix	Per-pixel Accuracy	85.0%	# 1
Image-to-Image Translation	Cityscapes Photo-to-Labels	pix2pix	Per-class Accuracy	40.0%	# 1
Image-to-Image Translation	Cityscapes Photo-to-Labels	pix2pix	Class IOU	0.32	# 1
Cross-View Image-to-Image Translation	cvusa	Pix2pix	SSIM	0.3923	# 7
Cross-View Image-to-Image Translation	Dayton (256×256) - aerial-to-ground	Pix2pix	SSIM	0.418	# 5
Cross-View Image-to-Image Translation	Dayton (256×256) - ground-to-aerial	Pix2pix	SSIM	0.2693	# 4
Cross-View Image-to-Image Translation	Dayton (64×64) - aerial-to-ground	Pix2pix	SSIM	0.4808	# 5
Cross-View Image-to-Image Translation	Dayton (64x64) - ground-to-aerial	Pix2pix	SSIM	0.3675	# 3
Image Reconstruction	Edge-to-Handbags	pix2pix	FID	96.31	# 4
Image Reconstruction	Edge-to-Handbags	pix2pix	LPIPS	0.234	# 1
Image Reconstruction	Edge-to-Shoes	pix2pix	FID	197.492	# 4
Image Reconstruction	Edge-to-Shoes	pix2pix	LPIPS	0.238	# 1
Cross-View Image-to-Image Translation	Ego2Top	Pix2pix	SSIM	0.2213	# 4
Fundus to Angiography Generation	Fundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients	pix2pix	FID	48.6	# 9
Colorization	ImageNet val	cGAN	FID-5K	24.41	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/image-to-image-translation-on-aerial-to-map)](https://paperswithcode.com/sota/image-to-image-translation-on-aerial-to-map?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/image-to-image-translation-on-cityscapes)](https://paperswithcode.com/sota/image-to-image-translation-on-cityscapes?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/image-to-image-translation-on-cityscapes-1)](https://paperswithcode.com/sota/image-to-image-translation-on-cityscapes-1?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/facial-expression-translation-on-ar-face)](https://paperswithcode.com/sota/facial-expression-translation-on-ar-face?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/nuclear-segmentation-on-cell17)](https://paperswithcode.com/sota/nuclear-segmentation-on-cell17?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on-1)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on-1?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on-3)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on-3?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/image-reconstruction-on-edge-to-handbags)](https://paperswithcode.com/sota/image-reconstruction-on-edge-to-handbags?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/image-reconstruction-on-edge-to-shoes)](https://paperswithcode.com/sota/image-reconstruction-on-edge-to-shoes?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on-5)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on-5?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/colorization-on-imagenet-val)](https://paperswithcode.com/sota/colorization-on-imagenet-val?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on-2)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on-2?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/cross-view-image-to-image-translation-on-4)](https://paperswithcode.com/sota/cross-view-image-to-image-translation-on-4?p=image-to-image-translation-with-conditional)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/image-to-image-translation-with-conditional/fundus-to-angiography-generation-on-fundus)](https://paperswithcode.com/sota/fundus-to-angiography-generation-on-fundus?p=image-to-image-translation-with-conditional)`

Image-to-Image Translation with Conditional Adversarial Networks

CVPR 2017 · Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros ·

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Indeed, since the release of the pix2pix software associated with this paper, a large number of internet users (many of them artists) have posted their own experiments with our system, further demonstrating its wide applicability and ease of adoption without the need for parameter tweaking. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without hand-engineering our loss functions either.

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Code

Add Remove Mark official

phillipi/pix2pix official

9,929

tensorflow/models

76,585

tensorflow/models

61,324

eriklindernoren/PyTorch-GAN

15,676

eriklindernoren/Keras-GAN

9,135

See all 175 implementations

Tasks

Add Remove

Colorization

Cross-View Image-to-Image Translation

Fundus to Angiography Generation

Image-to-Image Translation

Nuclear Segmentation

Translation

Datasets

Cityscapes

Sketch CVUSA

Dayton

Cell

Results from the Paper

Edit

Ranked #1 on Image-to-Image Translation on Cityscapes Photo-to-Labels

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Image-to-Image Translation	Aerial-to-Map	cGAN	Per-pixel Accuracy	70.0%	# 1	Compare
			Per-class Accuracy	46.0%	# 1	Compare
			Class IOU	0.26	# 1	Compare
Facial Expression Translation	AR Face	Enc.-Decoder	AMT	0.1	# 3	Compare
Facial Expression Translation	AR Face	Enc.-Decoder	PSNR	12.6660	# 3	Compare
Nuclear Segmentation	Cell17	Pix2Pix	F1-score	0.6208	# 4	Compare
			Dice	0.6351	# 3	Compare
			Hausdorff	19.1441	# 3	Compare
Image-to-Image Translation	Cityscapes Labels-to-Photo	pix2pix	Class IOU	0.18	# 1	Compare
			Per-class Accuracy	25.0	# 1	Compare
			Per-pixel Accuracy	71.0	# 8	Compare
			LPIPS	0	# 4	Compare
Image-to-Image Translation	Cityscapes Photo-to-Labels	pix2pix	Per-pixel Accuracy	85.0%	# 1	Compare
			Per-class Accuracy	40.0%	# 1	Compare
			Class IOU	0.32	# 1	Compare
Cross-View Image-to-Image Translation	cvusa	Pix2pix	SSIM	0.3923	# 7	Compare
Cross-View Image-to-Image Translation	Dayton (256×256) - aerial-to-ground	Pix2pix	SSIM	0.418	# 5	Compare
Cross-View Image-to-Image Translation	Dayton (256×256) - ground-to-aerial	Pix2pix	SSIM	0.2693	# 4	Compare
Cross-View Image-to-Image Translation	Dayton (64×64) - aerial-to-ground	Pix2pix	SSIM	0.4808	# 5	Compare
Cross-View Image-to-Image Translation	Dayton (64x64) - ground-to-aerial	Pix2pix	SSIM	0.3675	# 3	Compare
Cross-View Image-to-Image Translation	Ego2Top	Pix2pix	SSIM	0.2213	# 4	Compare
Fundus to Angiography Generation	Fundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients	pix2pix	FID	48.6	# 9	Compare
Colorization	ImageNet val	cGAN	FID-5K	24.41	# 4	Compare

Results from Other Papers

Task	Dataset	Model	Metric Name	Metric Value	Rank	Compare
Image Reconstruction	Edge-to-Handbags	pix2pix	FID	96.31	# 4	See all
Image Reconstruction	Edge-to-Handbags	pix2pix	LPIPS	0.234	# 1	See all
Image Reconstruction	Edge-to-Shoes	pix2pix	FID	197.492	# 4	See all
Image Reconstruction	Edge-to-Shoes	pix2pix	LPIPS	0.238	# 1	See all

Methods

Add Remove

Adam • Batch Normalization • ColorJitter • Concatenated Skip Connection • Convolution • Dropout • Leaky ReLU • PatchGAN • Pix2Pix • Random Resized Crop • ReLU • Sigmoid Activation

Edit Social Preview

Image-to-Image Translation with Conditional Adversarial Networks

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit