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 2001–2050 of 6689 papers

TitleStatusHype
Semantic Pyramid for Image GenerationCode1
Efficient Content-Based Sparse Attention with Routing TransformersCode1
Generalized Energy Based ModelsCode1
Π-nets: Deep Polynomial Neural NetworksCode1
MatchingGAN: Matching-based Few-shot Image GenerationCode1
SketchyCOCO: Image Generation from Freehand Scene SketchesCode1
GANwriting: Content-Conditioned Generation of Styled Handwritten Word ImagesCode1
Deep Image Spatial Transformation for Person Image GenerationCode1
A U-Net Based Discriminator for Generative Adversarial NetworksCode1
On Leveraging Pretrained GANs for Generation with Limited DataCode1
On Feature Normalization and Data AugmentationCode1
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANsCode1
CookGAN: Meal Image Synthesis from IngredientsCode1
Reliable Fidelity and Diversity Metrics for Generative ModelsCode1
VFlow: More Expressive Generative Flows with Variational Data AugmentationCode1
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable ModelsCode1
Latent Normalizing Flows for Many-to-Many Cross-Domain MappingsCode1
Learning to Generate Levels From NothingCode1
Hi-Net: Hybrid-fusion Network for Multi-modal MR Image SynthesisCode1
How to train your neural ODE: the world of Jacobian and kinetic regularizationCode1
Subspace Capsule NetworkCode1
Multi-Channel Attention Selection GANs for Guided Image-to-Image TranslationCode1
High-Fidelity Synthesis with Disentangled RepresentationCode1
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning NetworkCode1
A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningCode1
Bridging the Gap Between f-GANs and Wasserstein GANsCode1
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene GenerationCode1
CNN-generated images are surprisingly easy to spot... for nowCode1
Learning Canonical Representations for Scene Graph to Image GenerationCode1
Cloud Removal in Satellite Images Using Spatiotemporal Generative NetworksCode1
Controlling Style and Semantics in Weakly-Supervised Image GenerationCode1
StarGAN v2: Diverse Image Synthesis for Multiple DomainsCode1
Analyzing and Improving the Image Quality of StyleGANCode1
Flow Contrastive Estimation of Energy-Based ModelsCode1
Multi-marginal Wasserstein GANCode1
Bridging the Gap Between f-GANs and Wasserstein GANsCode1
Artistic Glyph Image Synthesis via One-Stage Few-Shot LearningCode1
Prescribed Generative Adversarial NetworksCode1
ZeRO: Memory Optimizations Toward Training Trillion Parameter ModelsCode1
Unsupervised Sketch-to-Photo SynthesisCode1
A Characteristic Function Approach to Deep Implicit Generative ModelingCode1
Image Synthesis From Reconfigurable Layout and StyleCode1
GAN Path Finder: Preliminary resultsCode1
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image GenerationCode1
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent RepresentationsCode1
Mean Spectral Normalization of Deep Neural Networks for Embedded AutomationCode1
Guided Image Generation with Conditional Invertible Neural NetworksCode1
Large Scale Adversarial Representation LearningCode1
Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNNCode1
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style TransferCode1
Show:102550
← PrevPage 41 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