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 1951–2000 of 6689 papers

TitleStatusHype
Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit DetectionCode1
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingCode1
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion ModelsCode1
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image GenerationCode1
Multi-marginal Wasserstein GANCode1
A Characteristic Function Approach to Deep Implicit Generative ModelingCode1
Ensembling Off-the-shelf Models for GAN TrainingCode1
A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and RestorationCode1
Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion ModelsCode1
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar ReconstructionCode1
Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image SynthesisCode1
Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood EstimationCode1
ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane ReflectionsCode1
One-Shot Learning for Pose-Guided Person Image Synthesis in the WildCode1
Multimodal LLM-Guided Semantic Correction in Text-to-Image DiffusionCode1
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry ImagesCode1
ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face SynthesisCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese DishesCode1
UIEDP:Underwater Image Enhancement with Diffusion PriorCode1
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion modelsCode1
Omni-GAN: On the Secrets of cGANs and BeyondCode1
A Survey on Deep Generative 3D-aware Image SynthesisCode1
Uncurated Image-Text Datasets: Shedding Light on Demographic BiasCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Conceptrol: Concept Control of Zero-shot Personalized Image GenerationCode1
Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured SequencesCode1
Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture SearchCode1
ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron PruningCode1
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image SynthesisCode1
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion ModelsCode1
NViSII: A Scriptable Tool for Photorealistic Image GenerationCode1
End-to-End Diffusion Latent Optimization Improves Classifier GuidanceCode1
Object-Centric Slot DiffusionCode1
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image SynthesisCode1
Concept Conductor: Orchestrating Multiple Personalized Concepts in Text-to-Image SynthesisCode1
End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure ImagesCode1
Enhanced Balancing GAN: Minority-class Image GenerationCode1
OCR-VQGAN: Taming Text-within-Image GenerationCode1
Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image SynthesisCode1
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksCode1
Edge-preserving noise for diffusion modelsCode1
One-Shot Structure-Aware Stylized Image SynthesisCode1
NaturalInversion: Data-Free Image Synthesis Improving Real-World ConsistencyCode1
Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value OptimizationCode1
Elucidating the solution space of extended reverse-time SDE for diffusion modelsCode1
Elucidating the design space of language models for image generationCode1
Negative Data AugmentationCode1
Elucidating the Exposure Bias in Diffusion ModelsCode1
No Token Left Behind: Explainability-Aided Image Classification and GenerationCode1
Show:102550
← PrevPage 40 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