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 3951–4000 of 6689 papers

TitleStatusHype
Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations—0
ReGround: Improving Textual and Spatial Grounding at No CostCode0
Deep Conditional HDRI: Inverse Tone Mapping via Dual Encoder-Decoder Conditioning Method—0
S2DM: Sector-Shaped Diffusion Models for Video Generation—0
IIDM: Image-to-Image Diffusion Model for Semantic Image SynthesisCode0
Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns InjectionCode0
BlendScape: Enabling End-User Customization of Video-Conferencing Environments through Generative AI—0
TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report GenerationCode0
Step-Calibrated Diffusion for Biomedical Optical Image RestorationCode0
DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception—0
Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques—0
IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models—0
AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation—0
Total Disentanglement of Font Images into Style and Character Class Features—0
Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Model—0
Segment Anything for comprehensive analysis of grapevine cluster architecture and berry properties—0
LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model—0
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory—0
Urban Scene Diffusion through Semantic Occupancy Map—0
QEAN: Quaternion-Enhanced Attention Network for Visual Dance GenerationCode0
HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data—0
Synthetic Image Generation in Cyber Influence Operations: An Emergent Threat?—0
A Survey on Quality Metrics for Text-to-Image Generation—0
A psychophysical evaluation of techniques for Mooney image generation—0
Enhancing GAN Performance through Neural Architecture Search and Tensor DecompositionCode0
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation—0
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm—0
Understanding Diffusion Models by Feynman's Path Integral—0
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient InversionCode0
Zippo: Zipping Color and Transparency Distributions into a Single Diffusion Model—0
Generative modeling of seismic data using score-based generative modelsCode0
StainDiffuser: MultiTask Dual Diffusion Model for Virtual Staining—0
Fast Personalized Text-to-Image Syntheses With Attention Injection—0
GazeFusion: Saliency-Guided Image Generation—0
StableGarment: Garment-Centric Generation via Stable Diffusion—0
Reward Guided Latent Consistency Distillation—0
Denoising Task Difficulty-based Curriculum for Training Diffusion Models—0
SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model—0
SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation—0
LightIt: Illumination Modeling and Control for Diffusion Models—0
Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder—0
Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling—0
Mitigating Data Consistency Induced Discrepancy in Cascaded Diffusion Models for Sparse-view CT Reconstruction—0
Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering—0
SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis—0
Noise Dimension of GAN: An Image Compression Perspective—0
Mitigating attribute amplification in counterfactual image generation—0
Make Me Happier: Evoking Emotions Through Image Diffusion Models—0
Unveiling the Truth: Exploring Human Gaze Patterns in Fake ImagesCode0
Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation—0
Show:102550
← PrevPage 80 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