image-generation

Conditional Image Generation

3260 papers • 126 benchmarks • 313 datasets

Conditional image generation is the task of generating new images from a dataset conditional on their class. ( Image credit: PixelCNN++ )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-generation

Trend

Dataset

Best Model

Actions

CIFAR-10

ImageNet 128x128

CIFAR-100

Libraries

i

Use these libraries to find image-generation models and implementations

open-mmlab/mmgeneration

5 papers 1,791

Datasets

Subtasks

Image-Guided Composition Human-Object Interaction Generation

Most implemented papers

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Soumith Chintala, Alec Radford, Luke Metz•Wed Nov 18 2015

This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.

14720

Content

ArtBench-10 (32x32)

ImageNet 256x256

ImageNet 64x64

COCO-Animals

Tiny ImageNet

CIFAR-10 LT

ImageNet-LT

eriklindernoren/PyTorch-GAN

3 papers 15,643

POSTECH-CVLab/PyTorch-StudioGAN

3 papers 3,361

minyoungg/pix2latent

2 papers 193

kynk94/TF2-Image-Generation

2 papers 27

lvyufeng/MindSpore-GAN

2 papers 22

Human-Art

Large Labelled Logo Dataset (L3D)

0

Paper Graph

Analyzing and Improving the Image Quality of StyleGAN

S. Laine, Timo Aila, Tero Karras, J. Lehtinen, M. Aittala, Janne Hellsten•Mon Dec 02 2019

This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.

6680 0

Paper Graph

Improved Training of Wasserstein GANs

Aaron C. Courville, Vincent Dumoulin, Martín Arjovsky, Ishaan Gulrajani, Faruk Ahmed•Thu Mar 30 2017

This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.

10496 0

Paper Graph

Conditional Image Synthesis with Auxiliary Classifier GANs

Jonathon Shlens, Augustus Odena, Christopher Olah•Sat Oct 29 2016

A variant of GANs employing label conditioning that results in 128 x 128 resolution image samples exhibiting global coherence is constructed and it is demonstrated that high resolution samples provide class information not present in low resolution samples.

3446 0

Paper Graph

Training Generative Adversarial Networks with Limited Data

S. Laine, Timo Aila, Tero Karras, J. Lehtinen, M. Aittala, Janne Hellsten•Sun May 31 2020

It is demonstrated, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images, and is expected to open up new application domains for GANs.

2135 0

Paper Graph

Self-Attention Generative Adversarial Networks

I. Goodfellow, Dimitris N. Metaxas, Augustus Odena, Han Zhang•Sun May 20 2018

The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.

4047 0

Paper Graph

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Bryan Catanzaro, Ming-Yu Liu, Jan Kautz, Jun-Yan Zhu, Ting-Chun Wang, Andrew Tao•Wed Nov 29 2017

A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.

4278 0

Paper Graph

Large Scale GAN Training for High Fidelity Natural Image Synthesis

Jeff Donahue, K. Simonyan, Andrew Brock•Wed Sep 26 2018

It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.

5949 0

Paper Graph

Diffusion Models Beat GANs on Image Synthesis

Alex Nichol, Prafulla Dhariwal•Mon May 10 2021

It is shown that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models, and classifier guidance combines well with upsampling diffusion models, further improving FID to 3.94 on ImageNet 256$\times$256 and 3.85 on imageNet 512$\ times$512.

10593 0

Paper Graph

Improved Techniques for Training GANs

I. Goodfellow, Alec Radford, Vicki Cheung, Tim Salimans, Xi Chen, Wojciech Zaremba•Thu Jun 09 2016

This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.

9942 0

Paper Graph

Adding a benchmark result helps the community track progress.