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 651–700 of 6689 papers

TitleStatusHype
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
The Stable Artist: Steering Semantics in Diffusion Latent SpaceCode2
Training-Free Structured Diffusion Guidance for Compositional Text-to-Image SynthesisCode2
Semantic-Conditional Diffusion Networks for Image CaptioningCode2
Wavelet Diffusion Models are fast and scalable Image GeneratorsCode2
Latent Video Diffusion Models for High-Fidelity Long Video GenerationCode2
Inversion-Based Style Transfer with Diffusion ModelsCode2
SinDiffusion: Learning a Diffusion Model from a Single Natural ImageCode2
Person Image Synthesis via Denoising Diffusion ModelCode2
Plug-and-Play Diffusion Features for Text-Driven Image-to-Image TranslationCode2
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and GenerationCode2
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image SynthesisCode2
A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent SpacesCode2
Latent-NeRF for Shape-Guided Generation of 3D Shapes and TexturesCode2
Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image GenerationCode2
eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert DenoisersCode2
Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and GuidanceCode2
What the DAAM: Interpreting Stable Diffusion Using Cross AttentionCode2
Building Normalizing Flows with Stochastic InterpolantsCode2
Personalizing Text-to-Image Generation via Aesthetic GradientsCode2
Poisson Flow Generative ModelsCode2
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
GAUDI: A Neural Architect for Immersive 3D Scene GenerationCode2
Unsupervised Medical Image Translation with Adversarial Diffusion ModelsCode2
Collaborative Neural Rendering using Anime Character SheetsCode2
Semantic Image Synthesis via Diffusion ModelsCode2
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change DetectionCode2
The ArtBench Dataset: Benchmarking Generative Models with ArtworksCode2
Blended Latent DiffusionCode2
Diffusion-GAN: Training GANs with DiffusionCode2
Improved Vector Quantized Diffusion ModelsCode2
Text2Human: Text-Driven Controllable Human Image GenerationCode2
IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait SynthesisCode2
Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and RegistrationCode2
BBDM: Image-to-image Translation with Brownian Bridge Diffusion ModelsCode2
Deep PCB To COCO ConvertorCode2
CogView2: Faster and Better Text-to-Image Generation via Hierarchical TransformersCode2
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pixCode2
VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language GuidanceCode2
Any-resolution Training for High-resolution Image SynthesisCode2
Neural Texture Extraction and Distribution for Controllable Person Image SynthesisCode2
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech SynthesisCode2
Make-A-Scene: Scene-Based Text-to-Image Generation with Human PriorsCode2
Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields TranslationCode2
Self-Distilled StyleGAN: Towards Generation from Internet PhotosCode2
Progressive Distillation for Fast Sampling of Diffusion ModelsCode2
StyleGAN-XL: Scaling StyleGAN to Large Diverse DatasetsCode2
Third Time's the Charm? Image and Video Editing with StyleGAN3Code2
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional LatentsCode2
Splicing ViT Features for Semantic Appearance TransferCode2
Show:102550
← PrevPage 14 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