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.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
Subtasks
Greatest papers with 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
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.
#5 best model for
Conditional Image Generation
on CIFAR-10
CONDITIONAL IMAGE GENERATION SEMI-SUPERVISED IMAGE CLASSIFICATION
Density estimation using Real NVP
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.
#3 best model for
Image Generation
on CIFAR-10
(Model Entropy metric)
Instance Normalization: The Missing Ingredient for Fast Stylization
• lengstrom/fast-style-transfer
•
It this paper we revisit the fast stylization method introduced in Ulyanov et.
A Style-Based Generator Architecture for Generative Adversarial Networks
• NVlabs/stylegan
•
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.
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.
#4 best model for
Conditional Image Generation
on ImageNet 128x128
Progressive Growing of GANs for Improved Quality, Stability, and Variation
We describe a new training methodology for generative adversarial networks.
SOTA for Image Generation on CIFAR-10
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.
#3 best model for
Image Generation
on CIFAR-10
(FID metric)
BEGAN: Boundary Equilibrium Generative Adversarial Networks
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks.
#12 best model for
Image Generation
on CIFAR-10
Semantic Image Synthesis with Spatially-Adaptive Normalization
• NVlabs/SPADE
• 
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout.