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 3701–3750 of 6689 papers

TitleStatusHype
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference—0
When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT—0
Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds—0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis—0
Multi-student Diffusion Distillation for Better One-step Generators—0
Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction—0
Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis—0
Multi-Task Adversarial Network for Disentangled Feature Learning—0
Multivariate Time Series Imputation with Generative Adversarial Networks—0
Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN—0
Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings—0
Multi-view Image Diffusion via Coordinate Noise and Fourier Attention—0
Multi-View Image Generation from a Single-View—0
Multi-View Unsupervised Image Generation with Cross Attention Guidance—0
GAN-Based Multi-View Video Coding with Spatio-Temporal EPI Reconstruction—0
Multi-view X-ray Image Synthesis with Multiple Domain Disentanglement from CT Scans—0
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data—0
Muon-Accelerated Attention Distillation for Real-Time Edge Synthesis via Optimized Latent Diffusion—0
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model—0
Anysize GAN: A solution to the image-warping problem—0
MuseumMaker: Continual Style Customization without Catastrophic Forgetting—0
Two-Stage Approach for Brain MR Image Synthesis: 2D Image Synthesis and 3D Refinement—0
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis—0
Two-stage Cytopathological Image Synthesis for Augmenting Cervical Abnormality Screening—0
Mutual Information Maximizing Quantum Generative Adversarial Network and Its Applications in Finance—0
Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images—0
M-VADER: A Model for Diffusion with Multimodal Context—0
AnyScene: Customized Image Synthesis with Composited Foreground—0
AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status—0
MVDD: Multi-View Depth Diffusion Models—0
AnyFace: Free-style Text-to-Face Synthesis and Manipulation—0
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures—0
Two-Stream Appearance Transfer Network for Person Image Generation—0
MVP: Multivariate polynomials for conditional generation—0
Learning Patterns in Sample Distributions for Monte Carlo Variance Reduction—0
My Art My Choice: Adversarial Protection Against Unruly AI—0
NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers—0
NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models—0
Type-R: Automatically Retouching Typos for Text-to-Image Generation—0
A Contrastive Learning Approach for Training Variational Autoencoder Priors—0
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models—0
NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface—0
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models—0
Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generation—0
AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models—0
UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception—0
NephroNet: A Novel Program for Identifying Renal Cell Carcinoma and Generating Synthetic Training Images with Convolutional Neural Networks and Diffusion Models—0
Nepotistically Trained Generative-AI Models Collapse—0
NeRF-Insert: 3D Local Editing with Multimodal Control Signals—0
Nested Annealed Training Scheme for Generative Adversarial Networks—0
Show:102550
← PrevPage 75 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