Browse SoTA > Computer Vision > Image Generation > Conditional Image Generation

Conditional Image Generation

50 papers with code · Computer Vision
Subtask of Image Generation

Conditional image generation is the task of generating new images from a dataset conditional on their class.

( Image credit: PixelCNN++ )

Benchmarks

Latest papers with code

Contrastive Generative Adversarial Networks

23 Jun 2020POSTECH-CVLab/PyTorch-StudioGAN

Simultaneously, the generator attempts to synthesize images to fool the discriminator and to maximize the mutual information of fake images from the same class prior.

CONDITIONAL IMAGE GENERATION DATA AUGMENTATION

135
23 Jun 2020

GANs in computer vision ebook

ebook 2020 The-AI-Summer/GANs-in-Computer-Vision

We do hope that this series will provide you a big overview of the field, so that you will not need to read all the literature by yourself, independent of your background on GANs.

CONDITIONAL IMAGE GENERATION IMAGE-TO-IMAGE TRANSLATION VIDEO GENERATION VIDEO-TO-VIDEO SYNTHESIS

7
10 Jun 2020

Reposing Humans by Warping 3D Features

8 Jun 2020MKnoche/warp3d_reposing

We address the problem of reposing an image of a human into any desired novel pose.

CONDITIONAL IMAGE GENERATION PERSON REPOSING POSE-GUIDED IMAGE GENERATION

5
08 Jun 2020

Melanoma Detection using Adversarial Training and Deep Transfer Learning

Journal of Physics in Medicine and Biology 2020 hasibzunair/adversarial-lesions

In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis by learning the inter-class mapping and synthesizing under-represented class samples from the over-represented ones using unpaired image-to-image translation.

ADVERSARIAL TRAINING CONDITIONAL IMAGE GENERATION IMAGE-TO-IMAGE TRANSLATION MEDICAL IMAGE GENERATION SKIN CANCER CLASSIFICATION SKIN LESION CLASSIFICATION TRANSFER LEARNING

9
14 Apr 2020

Attentive Normalization for Conditional Image Generation

CVPR 2020 shepnerd/AttenNorm

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.

CONDITIONAL IMAGE GENERATION SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY

35
08 Apr 2020

Feature Quantization Improves GAN Training

5 Apr 2020YangNaruto/FQ-GAN

The instability in GAN training has been a long-standing problem despite remarkable research efforts.

CONDITIONAL IMAGE GENERATION FACE GENERATION QUANTIZATION UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

96
05 Apr 2020

When Relation Networks meet GANs: Relation GANs with Triplet Loss

24 Feb 2020JosephineRabbit/Relation-GAN

Though recent research has achieved remarkable progress in generating realistic images with generative adversarial networks (GANs), the lack of training stability is still a lingering concern of most GANs, especially on high-resolution inputs and complex datasets.

CONDITIONAL IMAGE GENERATION

0
24 Feb 2020

Image Outpainting and Harmonization using Generative Adversarial Networks

23 Dec 2019etarthur/Outpainting

This way, the hallucinated details are integrated with the style of the original image, in an attempt to further boost the quality of the result and possibly allow for arbitrary output resolutions to be supported.

CONDITIONAL IMAGE GENERATION IMAGE OUTPAINTING

4
23 Dec 2019

cGANs with Multi-Hinge Loss

9 Dec 2019ilyakava/BigGAN-PyTorch

We propose a new algorithm to incorporate class conditional information into the discriminator of GANs via a multi-class generalization of the commonly used Hinge loss.

CONDITIONAL IMAGE GENERATION

17
09 Dec 2019