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 1001–1050 of 6689 papers

TitleStatusHype
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANCode1
Disentangled Representation Learning in Cardiac Image AnalysisCode1
C2N: Practical Generative Noise Modeling for Real-World DenoisingCode1
Anycost GANs for Interactive Image Synthesis and EditingCode1
Fair Diffusion: Instructing Text-to-Image Generation Models on FairnessCode1
FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian PerturbationCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Hierarchical Clustering for Conditional Diffusion in Image GenerationCode1
A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision TransformersCode1
ColorSwap: A Color and Word Order Dataset for Multimodal EvaluationCode1
Hierarchical Transformers Are More Efficient Language ModelsCode1
Diverse Image Generation via Self-Conditioned GANsCode1
Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster DataCode1
FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the EdgeCode1
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion ModelsCode1
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion ModelCode1
Combining Markov Random Fields and Convolutional Neural Networks for Image SynthesisCode1
Input Perturbation Reduces Exposure Bias in Diffusion ModelsCode1
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image SynthesisCode1
Unsupervised Sketch-to-Photo SynthesisCode1
BS-LDM: Effective Bone Suppression in High-Resolution Chest X-Ray Images with Conditional Latent Diffusion ModelsCode1
One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing FrameworkCode1
BS-Diff: Effective Bone Suppression Using Conditional Diffusion Models from Chest X-Ray ImagesCode1
Brush Your Text: Synthesize Any Scene Text on Images via Diffusion ModelCode1
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image DetectorsCode1
Diverse Image Synthesis from Semantic Layouts via Conditional IMLECode1
High Fidelity Image Synthesis With Deep VAEs In Latent SpaceCode1
Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion ModelsCode1
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image SynthesisCode1
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingCode1
Distribution-Aware Data Expansion with Diffusion ModelsCode1
GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial NetworksCode1
Bridging the Gap Between f-GANs and Wasserstein GANsCode1
Bridging the Gap Between f-GANs and Wasserstein GANsCode1
DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-EncoderCode1
Handwriting TransformersCode1
HealthiVert-GAN: A Novel Framework of Pseudo-Healthy Vertebral Image Synthesis for Interpretable Compression Fracture GradingCode1
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
Dissecting and Mitigating Diffusion Bias via Mechanistic InterpretabilityCode1
Dissolving Is Amplifying: Towards Fine-Grained Anomaly DetectionCode1
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion ModelsCode1
Guided Image Generation with Conditional Invertible Neural NetworksCode1
Towards Disentangling Latent Space for Unsupervised Semantic Face EditingCode1
DMM: Building a Versatile Image Generation Model via Distillation-Based Model MergingCode1
An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image SynthesisCode1
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial NetworkCode1
High-Fidelity Neural Human Motion Transfer from Monocular VideoCode1
GRAF: Generative Radiance Fields for 3D-Aware Image SynthesisCode1
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image GenerationCode1
Graph Image Prior for Unsupervised Dynamic Cardiac Cine MRI ReconstructionCode1
Show:102550
← PrevPage 21 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