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

Showing 19511975 of 6689 papers

TitleStatusHype
MTSS-GAN: Multivariate Time Series Simulation Generative Adversarial NetworksCode1
Locally Masked Convolution for Autoregressive ModelsCode1
Deep Polynomial Neural NetworksCode1
Diverse Image Generation via Self-Conditioned GANsCode1
Auxiliary-task learning for geographic data with autoregressive embeddingsCode1
Improving GAN Training with Probability Ratio Clipping and Sample ReweightingCode1
GANs in computer vision ebookCode1
Probabilistic AutoencoderCode1
Super-resolution Variational Auto-EncodersCode1
Reposing Humans by Warping 3D FeaturesCode1
Learning Texture Transformer Network for Image Super-ResolutionCode1
P-nets: Deep Polynomial Neural NetworksCode1
Network-to-Network Translation with Conditional Invertible Neural NetworksCode1
S2IGAN: Speech-to-Image Generation via Adversarial LearningCode1
Conditional Image Generation and Manipulation for User-Specified ContentCode1
CONFIG: Controllable Neural Face Image GenerationCode1
Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image SynthesisCode1
Editing in Style: Uncovering the Local Semantics of GANsCode1
A Disentangling Invertible Interpretation Network for Explaining Latent RepresentationsCode1
Disentangled Image Generation Through Structured Noise InjectionCode1
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive LearningCode1
Efficient Neural Architecture for Text-to-Image SynthesisCode1
Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRICode1
Generative Feature Replay For Class-Incremental LearningCode1
Training with Quantization Noise for Extreme Model CompressionCode1
Show:102550
← PrevPage 79 of 268Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3Unverified
2ADMFID11.84Unverified
3BigGAN-deepFID8.1Unverified
4Polarity-BigGANFID6.82Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59Unverified
6MaskGITFID6.18Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2Unverified
8CDMFID4.88Unverified
9ADM-GFID4.59Unverified
10RINFID4.51Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2Unverified
2RESFLOWFID48.29Unverified
3Residual FlowFID46.37Unverified
4GLF+perceptual loss (ours)FID44.6Unverified
5ProdPoly no activation functionsFID40.45Unverified
6ProdPoly no activation functionsFID36.77Unverified
7ACGANFID35.47Unverified
8DenseFlow-74-10FID34.9Unverified
9NVAE w/ flowFID32.53Unverified
10QSNGANFID31.97Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87Unverified
2GLIDE + CLIPFID30.46Unverified
3GLIDE + CLS-FREEFID29.22Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18Unverified
5PGMGANFID21.73Unverified
6CLR-GANFID20.27Unverified
7FMFID14.45Unverified
8CT (Direct Generation, NFE=1)FID13Unverified
9CT (Direct Generation, NFE=2)FID11.1Unverified
10GLIDE +CLSKID7.95Unverified