Image Generation

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 )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 6226–6250 of 6689 papers

Title	Date	Tasks	Status	Hype
LumiPath -- Towards Real-time Physically-based Rendering on Embedded Devices	Mar 9, 2019	Data VisualizationImage Generation	CodeCode Available	0
Reference-based Variational Autoencoders	Mar 8, 2019	AttributeConditional Image Generation	—Unverified	0
Adversarial Out-domain Examples for Generative Models	Mar 7, 2019	Adversarial AttackImage Generation	CodeCode Available	0
Attack Type Agnostic Perceptual Enhancement of Adversarial Images	Mar 7, 2019	Adversarial AttackImage Generation	—Unverified	0
High-Fidelity Image Generation With Fewer Labels	Mar 6, 2019	Conditional Image GenerationImage Generation	—Unverified	0
DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis	Mar 6, 2019	Image GenerationSuper-Resolution	—Unverified	0
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model	Feb 28, 2019	Image GenerationImage-to-Image Translation	—Unverified	0
Object-driven Text-to-Image Synthesis via Adversarial Training	Feb 27, 2019	Image GenerationObject	CodeCode Available	0
Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation	Feb 25, 2019	Conditional Image GenerationDiversity	—Unverified	0
Anomaly Detection with Adversarial Dual Autoencoders	Feb 19, 2019	Anomaly DetectionImage Generation	CodeCode Available	0
Fully-Featured Attribute Transfer	Feb 17, 2019	AttributeImage Generation	—Unverified	0
Adversarially Approximated Autoencoder for Image Generation and Manipulation	Feb 14, 2019	Generative Adversarial NetworkImage Generation	—Unverified	0
Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images	Feb 12, 2019	BIG-bench Machine LearningGeneral Classification	—Unverified	0
MaCow: Masked Convolutional Generative Flow	Feb 12, 2019	Computational EfficiencyDensity Estimation	CodeCode Available	1
Unpriortized Autoencoder For Image Generation	Feb 12, 2019	Density EstimationImage Generation	—Unverified	0
Synthesizing New Retinal Symptom Images by Multiple Generative Models	Feb 11, 2019	General ClassificationImage Generation	CodeCode Available	0
Photorealistic Image Synthesis for Object Instance Detection	Feb 9, 2019	6D Pose Estimation6D Pose Estimation using RGB	—Unverified	0
Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning	Feb 7, 2019	Image GenerationImage-to-Image Translation	—Unverified	0
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling	Feb 6, 2019	Anomaly DetectionAttribute	CodeCode Available	1
Active Image Synthesis for Efficient Labeling	Feb 5, 2019	Image GenerationSmall Data Image Classification	—Unverified	0
Realistic Image Generation using Region-phrase Attention	Feb 4, 2019	Generative Adversarial NetworkImage Generation	—Unverified	0
Compatible and Diverse Fashion Image Inpainting	Feb 4, 2019	Fashion SynthesisImage Generation	—Unverified	0
A Layer-Based Sequential Framework for Scene Generation with GANs	Feb 2, 2019	Conditional Image GenerationImage Generation	CodeCode Available	0
Collaborative Sampling in Generative Adversarial Networks	Feb 2, 2019	Image Generation	CodeCode Available	0
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design	Feb 1, 2019	Computational EfficiencyDensity Estimation	CodeCode Available	0

Show:10 25 50

← PrevPage 250 of 268Next →

All datasets ImageNet 256x256 CIFAR-10 ImageNet 64x64 ImageNet 512x512 FFHQ 256 x 256 CelebA 64x64 ImageNet 32x32 LSUN Bedroom 256 x 256 STL-10 LSUN Churches 256 x 256 ImageNet 128x128 FFHQ 1024 x 1024

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Improved DDPM	FID	12.3	—	Unverified
2	ADM	FID	11.84	—	Unverified
3	BigGAN-deep	FID	8.1	—	Unverified
4	Polarity-BigGAN	FID	6.82	—	Unverified
5	VQGAN+Transformer (k=mixed, p=1.0, a=0.005)	FID	6.59	—	Unverified
6	MaskGIT	FID	6.18	—	Unverified
7	VQGAN+Transformer (k=600, p=1.0, a=0.05)	FID	5.2	—	Unverified
8	CDM	FID	4.88	—	Unverified
9	ADM-G	FID	4.59	—	Unverified
10	RIN	FID	4.51	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PresGAN	FID	52.2	—	Unverified
2	RESFLOW	FID	48.29	—	Unverified
3	Residual Flow	FID	46.37	—	Unverified
4	GLF+perceptual loss (ours)	FID	44.6	—	Unverified
5	ProdPoly no activation functions	FID	40.45	—	Unverified
6	ProdPoly no activation functions	FID	36.77	—	Unverified
7	ACGAN	FID	35.47	—	Unverified
8	DenseFlow-74-10	FID	34.9	—	Unverified
9	NVAE w/ flow	FID	32.53	—	Unverified
10	QSNGAN	FID	31.97	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GLIDE + CLS	FID	30.87	—	Unverified
2	GLIDE + CLIP	FID	30.46	—	Unverified
3	GLIDE + CLS-FREE	FID	29.22	—	Unverified
4	GLIDE + CLIP + CLS + CLS-FREE	FID	29.18	—	Unverified
5	PGMGAN	FID	21.73	—	Unverified
6	CLR-GAN	FID	20.27	—	Unverified
7	FM	FID	14.45	—	Unverified
8	CT (Direct Generation, NFE=1)	FID	13	—	Unverified
9	CT (Direct Generation, NFE=2)	FID	11.1	—	Unverified
10	GLIDE +CLS	KID	7.95	—	Unverified