Image Generation

Edit

295 papers with code · Computer Vision

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 )

Leaderboards

Add a Result

DATASET	BEST METHOD	PAPER TITLE	COMPARE
CIFAR-10	NCSN	Generative Modeling by Estimating Gradients of the Data Distribution	See all
ImageNet 64x64	Sparse Transformer 152M (strided)	Generating Long Sequences with Sparse Transformers	See all
LSUN Bedroom 256 x 256	COCO-GAN	COCO-GAN: Generation by Parts via Conditional Coordinating	See all
CelebA-HQ 1024x1024	StyleGAN	A Style-Based Generator Architecture for Generative Adversarial Networks	See all
FFHQ	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
ImageNet 32x32	Flow++	Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design	See all
CelebA 256x256	MaCow (Var)	MaCow: Masked Convolutional Generative Flow	See all
MNIST	Residual Flow	Residual Flows for Invertible Generative Modeling	See all
CelebA-HQ 128x128	COCO-GAN	COCO-GAN: Generation by Parts via Conditional Coordinating	See all
CAT 256x256	RaSGAN	The relativistic discriminator: a key element missing from standard GAN	See all
LSUN Churches 256 x 256	StyleGAN2	Analyzing and Improving the Image Quality of StyleGAN	See all
Oxford 102 Flowers 256 x 256	MSG-StyleGAN	MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis	See all
ADE-Indoor	SB-GAN	Semantic Bottleneck Scene Generation	See all
Cityscapes-5K 256x512	SB-GAN	Semantic Bottleneck Scene Generation	See all
Indian Celebs 256 x 256	MSG-StyleGAN	MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis	See all
CIFAR-100	MSGAN	Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game	See all
CelebA	COCO-GAN	COCO-GAN: Generation by Parts via Conditional Coordinating	See all
Cityscapes-25K 256x512	SB-GAN	Semantic Bottleneck Scene Generation	See all

Subtasks

Image-to-Image Translation

27 leaderboards

119 papers with code

Image Inpainting

6 leaderboards

69 papers with code

Conditional Image Generation

2 leaderboards

41 papers with code

Face Generation

7 leaderboards

24 papers with code

Text-to-Image Generation

5 leaderboards

14 papers with code

See all 10 subtasks

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.

#16 best model for Image Generation on CIFAR-10 (NLL Test metric)

DENSITY ESTIMATION IMAGE GENERATION

62,639

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.

#5 best model for Unsupervised MNIST on MNIST

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.

#8 best model for Conditional Image Generation on CIFAR-10

CONDITIONAL IMAGE GENERATION SEMI-SUPERVISED IMAGE CLASSIFICATION

61,324

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.

#7 best model for Conditional Image Generation on ImageNet 128x128