SOTAVerified

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.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5551–5600 of 6689 papers

TitleStatusHype
Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator—0
Generative Neurosymbolic MachinesCode1
CellCycleGAN: Spatiotemporal Microscopy Image Synthesis of Cell Populations using Statistical Shape Models and Conditional GANs—0
Few-Shot Adaptation of Generative Adversarial NetworksCode1
One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGANCode1
Synthesis of COVID-19 Chest X-rays using Unpaired Image-to-Image TranslationCode1
LT-GAN: Self-Supervised GAN with Latent Transformation Detection—0
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational AutoencodersCode0
Training Generative Adversarial Networks via stochastic Nash games—0
New Ideas and Trends in Deep Multimodal Content Understanding: A Review—0
Semantic Editing On Segmentation Map Via Multi-Expansion Loss—0
The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems—0
A Human Eye-based Text Color Scheme Generation Method for Image Synthesis—0
Random Network Distillation as a Diversity Metric for Both Image and Text Generation—0
Experimental Quantum Generative Adversarial Networks for Image GenerationCode0
Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 NetworkCode1
Omni-Directional Image Generation from Single Snapshot ImageCode0
Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between DomainsCode1
Image Generation With Neural Cellular AutomatasCode1
Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed ImagesCode1
A disentangled generative model for disease decomposition in chest X-rays via normal image synthesisCode1
Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANsCode1
A Contrastive Learning Approach for Training Variational Autoencoder Priors—0
Denoising Diffusion Implicit ModelsCode2
Arbitrary Style Transfer using Graph Instance Normalization—0
Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images—0
Image Translation for Medical Image Generation -- Ischemic Stroke LesionsCode0
Data Augmentation Based Malware Detection using Convolutional Neural NetworksCode1
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov WassersteinCode1
Generating Gameplay-Relevant Art Assets with Transfer LearningCode0
MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination—0
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based ModelsCode1
Implicit Rank-Minimizing AutoencoderCode1
Tabular GANs for uneven distributionCode0
RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse priorCode1
Rethinking Attention with PerformersCode2
EEG to fMRI Synthesis: Is Deep Learning a candidate?—0
TinyGAN: Distilling BigGAN for Conditional Image GenerationCode1
Data Instance Prior for Transfer Learning in GANs—0
Simplifying Models with Unlabeled Output Data—0
Triple-GAN with Variable Fractional Order Gradient Descent Method and Mish Activation Function—0
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal TransformersCode1
Scene Graph to Image Generation with Contextualized Object Layout Refinement—0
Adversarial Rain Attack and Defensive Deraining for DNN Perception—0
Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering—0
Conditional Image Generation with One-Vs-All Classifier—0
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific DeltaCode1
Synthetic Convolutional Features for Improved Semantic Segmentation—0
Deep Sinogram Completion with Image Prior for Metal Artifact Reduction in CT Images—0
TreeGAN: Incorporating Class Hierarchy into Image Generation—0
Show:102550
← PrevPage 112 of 134Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified