Conditional Image Generation
133 papers with code • 10 benchmarks • 8 datasets
Conditional image generation is the task of generating new images from a dataset conditional on their class.
( Image credit: PixelCNN++ )
Benchmarks
These leaderboards are used to track progress in Conditional Image Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Conditional Image Generation models and implementationsDatasets
CIFAR-10
MS COCO
CIFAR-100
Tiny ImageNet
ImageNet-LT
ArtBench-10 (32x32)
Most implemented papers
Is Attention Better Than Matrix Decomposition?
Gsunshine/Enjoy-Hamburger
•
•
ICLR 2021
As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery.
Projected GANs Converge Faster
autonomousvision/projected_gan
•
•
NeurIPS 2021
Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train.
Autoregressive Image Generation using Residual Quantization
kakaobrain/rq-vae-transformer
•
•
CVPR 2022
However, we postulate that previous VQ cannot shorten the code sequence and generate high-fidelity images together in terms of the rate-distortion trade-off.
All are Worth Words: A ViT Backbone for Diffusion Models
We evaluate U-ViT in unconditional and class-conditional image generation, as well as text-to-image generation tasks, where U-ViT is comparable if not superior to a CNN-based U-Net of a similar size.
Stacked Generative Adversarial Networks
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network.
GP-GAN: Towards Realistic High-Resolution Image Blending
wuhuikai/GP-GAN
•
•
Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place.
Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork
cs-chan/ArtGAN
•
•
Qualitatively, we demonstrate that ArtGAN is able to generate plausible-looking images on Oxford-102 and CUB-200, as well as able to draw realistic artworks based on style, artist, and genre.
A Variational U-Net for Conditional Appearance and Shape Generation
Experiments show that the model enables conditional image generation and transfer.
Unsupervised Learning of Object Landmarks through Conditional Image Generation
tomasjakab/imm
•
•
NeurIPS 2018
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision.
