Image Generation
Image generation (synthesis) is the task of generating new images from an existing dataset.
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. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation.
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. We focus on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic.
#5 best model for
Conditional Image Generation on CIFAR-10
Density estimation using Real NVP
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task.
#14 best model for
Image Generation on CIFAR-10
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. We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images.
Self-Attention Generative Adversarial Networks
• 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. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps.
#2 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. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses.
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. However, the convergence of GAN training has still not been proved.
#2 best model for
Image Generation on LSUN Bedroom 256 x 256
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. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis.
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. This method balances the generator and discriminator during training.
#10 best model for
Image Generation on CIFAR-10
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
CVPR 2016
• awentzonline/image-analogies
•
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level.