Image Generation Edit Task

Computer Vision

530

papers with code

benchmarks

datasets

About
Edit

Image generation (synthesis) is the task of generating new images from an existing dataset.

Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Benchmarks

Add a Result

DATASET	BEST METHOD	PAPER TITLE	COMPARE
CIFAR-10	NCSN++ cont. (deep, VE)	Score-Based Generative Modeling through Stochastic Differential Equations	See all
ImageNet 32x32	Image Transformer	Image Transformer	See all
ImageNet 64x64	Routing Transformer	Efficient Content-Based Sparse Attention with Routing Transformers	See all
CelebA 256x256	SPN Menick and Kalchbrenner (2019)	Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling	See all
STL-10	TransGAN	TransGAN: Two Transformers Can Make One Strong GAN	See all
LSUN Bedroom 256 x 256	StyleGAN	A Style-Based Generator Architecture for Generative Adversarial Networks	See all
MNIST	Locally Masked PixelCNN (8 orders)	Locally Masked Convolution for Autoregressive Models	See all
Binarized MNIST	Locally Masked PixelCNN (8 orders)	Locally Masked Convolution for Autoregressive Models	See all
FFHQ	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
CelebA-HQ 128x128	U-Net GAN	A U-Net Based Discriminator for Generative Adversarial Networks	See all
LSUN Churches 256 x 256	CIPS	Image Generators with Conditionally-Independent Pixel Synthesis	See all
FFHQ 256 x 256	StyleGAN2 ADA+bCR	Training Generative Adversarial Networks with Limited Data	See all
CelebA-HQ 1024x1024	StyleGAN	A Style-Based Generator Architecture for Generative Adversarial Networks	See all
ImageNet 128x128	BigGAN-deep	Large Scale GAN Training for High Fidelity Natural Image Synthesis	See all
CelebA-HQ 64x64	VAEBM	VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models	See all
CelebA 64x64	NCP-VAE	NCP-VAE: Variational Autoencoders with Noise Contrastive Priors	See all
CelebA-HQ 256x256	PGGAN	Progressive Growing of GANs for Improved Quality, Stability, and Variation	See all
CIFAR-100	TAC-GAN	Twin Auxilary Classifiers GAN	See all
Fashion-MNIST	GLF+perceptual loss (ours)	Generative Latent Flow	See all
Stacked MNIST	VAEBM	VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models	See all
CUB 128 x 128	FineGAN	FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery	See all
Stanford Dogs	FineGAN	FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery	See all
Stanford Cars	FineGAN	FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery	See all
LSUN Cat 256 x 256	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
CelebA 128x128	U-Net GAN	A U-Net Based Discriminator for Generative Adversarial Networks	See all
CIFAR-10 (20% data)	DiffAugment-StyleGAN2	Differentiable Augmentation for Data-Efficient GAN Training	See all
CIFAR-10 (10% data)	DiffAugment-StyleGAN2	Differentiable Augmentation for Data-Efficient GAN Training	See all
CAT 256x256	RaSGAN	The relativistic discriminator: a key element missing from standard GAN	See all
CelebA 128 x 128	COCO-GAN	COCO-GAN: Generation by Parts via Conditional Coordinating	See all
LSUN Bedroom 64 x 64	WGAN-GP + TT Update Rule	GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium	See all
FFHQ 1024 x 1024	StyleGAN2 ADA+bCR	Training Generative Adversarial Networks with Limited Data	See all
Cityscapes-5K 256x512	SB-GAN	Semantic Bottleneck Scene Generation	See all
Cityscapes-25K 256x512	SB-GAN	Semantic Bottleneck Scene Generation	See all
ADE-Indoor	SB-GAN	Semantic Bottleneck Scene Generation	See all
Indian Celebs 256 x 256	MSG-StyleGAN	MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks	See all
Oxford 102 Flowers 256 x 256	MSG-StyleGAN	MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks	See all
LSUN Car 256 x 256	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
LSUN Horse 256 x 256	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
LSUN Car 512 x 384	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
Multi-dSprites	GENESIS	GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations	See all
GQN	GENESIS	GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations	See all
Landscapes 256 x 256	CIPS	Image Generators with Conditionally-Independent Pixel Synthesis	See all
Satellite-Buildings 256 x 256	CIPS	Image Generators with Conditionally-Independent Pixel Synthesis	See all
Satellite-Landscapes 256 x 256	CIPS	Image Generators with Conditionally-Independent Pixel Synthesis	See all
LSUN Bedroom 128 x 128	DC-VAE	Dual Contradistinctive Generative Autoencoder	See all

Subtasks

Image-to-Image Translation

47 benchmarks

219 papers with code

Image Inpainting

10 benchmarks

109 papers with code

Conditional Image Generation

5 benchmarks

64 papers with code

Face Generation

11 benchmarks

42 papers with code

Text-to-Image Generation

6 benchmarks

18 papers with code

See all 14 subtasks

Datasets

CIFAR-10

STL-10

MNIST

Binarized MNIST

FFHQ

See all 34 datasets

Greatest papers with code

Density estimation using Real NVP

27 May 2016 • tensorflow/models •

Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.

Ranked #11 on Image Generation on ImageNet 32x32

DENSITY ESTIMATION IMAGE GENERATION

68,875

Paper
Code

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

NeurIPS 2016 • tensorflow/models •

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.

Ranked #2 on Image Generation on Stanford Dogs

IMAGE GENERATION REPRESENTATION LEARNING UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST

61,324

Paper
Code

Improved Techniques for Training GANs

NeurIPS 2016 • tensorflow/models •

We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.

Ranked #11 on Conditional Image Generation on CIFAR-10

CONDITIONAL IMAGE GENERATION SEMI-SUPERVISED IMAGE CLASSIFICATION

61,324

Paper
Code

A General and Adaptive Robust Loss Function

CVPR 2019 • google-research/google-research •

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions.

IMAGE GENERATION

16,128

Paper
Code

Self-Attention Generative Adversarial Networks

arXiv 2018 • jantic/DeOldify •

In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.

Ranked #10 on Conditional Image Generation on ImageNet 128x128

CONDITIONAL IMAGE GENERATION

12,996

Paper
Code

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

NeurIPS 2017 • jantic/DeOldify •

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible.

Ranked #1 on Image Generation on LSUN Bedroom 64 x 64

IMAGE GENERATION

12,996

Paper
Code

A Style-Based Generator Architecture for Generative Adversarial Networks

CVPR 2019 • NVlabs/stylegan •

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.

Ranked #1 on Image Generation on LSUN Bedroom 256 x 256

IMAGE GENERATION

10,804

Paper
Code

Instance Normalization: The Missing Ingredient for Fast Stylization

27 Jul 2016 • lengstrom/fast-style-transfer •

It this paper we revisit the fast stylization method introduced in Ulyanov et.

IMAGE GENERATION IMAGE STYLIZATION

9,731

Paper
Code

Generating Diverse High-Fidelity Images with VQ-VAE-2

NeurIPS 2019 • deepmind/sonnet •

We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation.

IMAGE GENERATION

8,777

Paper
Code

The relativistic discriminator: a key element missing from standard GAN

ICLR 2019 • eriklindernoren/PyTorch-GAN •

We show that this property can be induced by using a relativistic discriminator which estimate the probability that the given real data is more realistic than a randomly sampled fake data.

Ranked #1 on Image Generation on CAT 256x256

IMAGE GENERATION

8,701

Paper
Code

Image Generation Edit Task

About Edit

Benchmarks Add a Result

Subtasks

Image-to-Image Translation

Image Inpainting

Conditional Image Generation

Face Generation

Text-to-Image Generation

Datasets

CIFAR-10

STL-10

MNIST

Binarized MNIST

FFHQ

Greatest papers with code

About
Edit

Benchmarks

Add a Result