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 1251–1300 of 6689 papers

TitleStatusHype
Inferring and Leveraging Parts from Object Shape for Improving Semantic Image SynthesisCode1
AdaNAT: Exploring Adaptive Policy for Token-Based Image GenerationCode1
Cross Initialization for Personalized Text-to-Image GenerationCode1
AutoStory: Generating Diverse Storytelling Images with Minimal Human EffortCode1
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative ModelsCode1
IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion ModelsCode1
Cross-domain Correspondence Learning for Exemplar-based Image TranslationCode1
Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit EditingCode1
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsCode1
Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic Models for Blind Super-Resolution Reconstruction in RSIsCode1
Incorporating long-range consistency in CNN-based texture generationCode1
InfinityGAN: Towards Infinite-Pixel Image SynthesisCode1
Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image GenerationCode1
Cross Attention Based Style Distribution for Controllable Person Image SynthesisCode1
DRAW: A Recurrent Neural Network For Image GenerationCode1
DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model StatisticsCode1
CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal DiffusionCode1
Improving the Speed and Quality of GAN by Adversarial TrainingCode1
AutoSplice: A Text-prompt Manipulated Image Dataset for Media ForensicsCode1
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 BenchmarkCode1
DPImageBench: A Unified Benchmark for Differentially Private Image SynthesisCode1
Improving Virtual Try-On with Garment-focused Diffusion ModelsCode1
DMM: Building a Versatile Image Generation Model via Distillation-Based Model MergingCode1
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Dual Attention GANs for Semantic Image SynthesisCode1
Dual Contrastive Loss and Attention for GANsCode1
DocSynth: A Layout Guided Approach for Controllable Document Image SynthesisCode1
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image SynthesisCode1
Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised ApproachCode1
Improving Text-to-Image Synthesis Using Contrastive LearningCode1
Dual Pyramid Generative Adversarial Networks for Semantic Image SynthesisCode1
Efficient-VDVAE: Less is moreCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
AMO Sampler: Enhancing Text Rendering with OvershootingCode1
Diversity-aware Channel Pruning for StyleGAN CompressionCode1
Cross-View Image Synthesis using Conditional GANsCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Harnessing LLM to Attack LLM-Guarded Text-to-Image ModelsCode1
Improving the Fairness of Deep Generative Models without RetrainingCode1
Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text GuidanceCode1
Improving Visual Commonsense in Language Models via Multiple Image GenerationCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Diverse Image Generation via Self-Conditioned GANsCode1
Autoregressive Diffusion ModelsCode1
Improving GANs for Long-Tailed Data through Group Spectral RegularizationCode1
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
Improving Few-shot Image Generation by Structural Discrimination and Textural ModulationCode1
Editing in Style: Uncovering the Local Semantics of GANsCode1
Improving GAN Training with Probability Ratio Clipping and Sample ReweightingCode1
DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-EncoderCode1
Show:102550
← PrevPage 26 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