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 1751–1800 of 6689 papers

TitleStatusHype
GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content—0
Self-Improving Diffusion Models with Synthetic Data—0
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
GRPose: Learning Graph Relations for Human Image Generation with Pose PriorsCode2
Enhancing Conditional Image Generation with Explainable Latent Space ManipulationCode0
CSGO: Content-Style Composition in Text-to-Image Generation—0
Spiking Diffusion ModelsCode2
GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative ModelsCode0
ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual GroundingCode0
Merging and Splitting Diffusion Paths for Semantically Coherent PanoramasCode1
Disentangled Diffusion Autoencoder for Harmonization of Multi-site Neuroimaging Data—0
Hand1000: Generating Realistic Hands from Text with Only 1,000 Images—0
CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization—0
Reflective Human-Machine Co-adaptation for Enhanced Text-to-Image Generation Dialogue System—0
Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generation—0
Sequential-Scanning Dual-Energy CT Imaging Using High Temporal Resolution Image Reconstruction and Error-Compensated Material Basis Image Generation—0
Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation—0
CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis—0
Alfie: Democratising RGBA Image Generation With No $Code2
DIAGen: Diverse Image Augmentation with Generative ModelsCode1
GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned PolicyCode2
Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models—0
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty—0
Variational autoencoder-based neural network model compression—0
SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian SplattingCode2
HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models—0
Prior Learning in Introspective VAEs—0
Explainable Concept Generation through Vision-Language Preference Learning—0
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
Prompt-Softbox-Prompt: A free-text Embedding Control for Image Editing—0
Shape-Preserving Generation of Food Images for Automatic Dietary Assessment—0
Abstract Art Interpretation Using ControlNetCode0
EasyControl: Transfer ControlNet to Video Diffusion for Controllable Generation and Interpolation—0
G3FA: Geometry-guided GAN for Face Animation—0
What Do You Want? User-centric Prompt Generation for Text-to-image Synthesis via Multi-turn GuidanceCode0
DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models—0
Scalable Autoregressive Image Generation with MambaCode2
Dynamic Product Image Generation and Recommendation at Scale for Personalized E-commerce—0
Show-o: One Single Transformer to Unify Multimodal Understanding and GenerationCode5
MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient—0
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion—0
CODE: Confident Ordinary Differential EditingCode0
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
Pixel Is Not A Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models—0
Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models—0
Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets ProtectionCode0
UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and GenerationCode1
FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting—0
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further TuningCode2
MS^3D: A RG Flow-Based Regularization for GAN Training with Limited Data—0
Show:102550
← PrevPage 36 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