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 5651–5700 of 6689 papers

TitleStatusHype
Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model—0
Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion—0
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion—0
Simple Transparent Adversarial Examples—0
Simple U-net Based Synthetic Polyp Image Generation: Polyp to Negative and Negative to Polyp—0
Simplex Autoencoders—0
Simplifying Models with Unlabeled Output Data—0
Simulation of an Elevator Group Control Using Generative Adversarial Networks and Related AI Tools—0
Simultaneous Multiple-Prompt Guided Generation Using Differentiable Optimal Transport—0
Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Coding—0
Vector Quantized Image-to-Image Translation—0
YoChameleon: Personalized Vision and Language Generation—0
Adversarial Attacks on Image Generation With Made-Up Words—0
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification—0
Vehicle Image Generation Going Well with The Surroundings—0
Single-Image 3D Human Digitization with Shape-Guided Diffusion—0
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis—0
Adversarial Attack Against Images Classification based on Generative Adversarial Networks—0
Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes—0
SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing—0
Advancing Video Quality Assessment for AIGC—0
Single Stage Multi-Pose Virtual Try-On—0
Single Underwater Image Enhancement Using an Analysis-Synthesis Network—0
Single-View Height Estimation with Conditional Diffusion Probabilistic Models—0
Advancing Urban Renewal: An Automated Approach to Generating Historical Arcade Facades with Stable Diffusion Models—0
SKE-Layout: Spatial Knowledge Enhanced Layout Generation with LLMs—0
Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Control—0
Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation—0
Advancing Text-Driven Chest X-Ray Generation with Policy-Based Reinforcement Learning—0
Enhancing Diffusion-Based Image Synthesis with Robust Classifier GuidanceCode0
Enhancing Diffusion Models Efficiency by Disentangling Total-Variance and Signal-to-Noise RatioCode0
TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report GenerationCode0
Relational Diffusion Distillation for Efficient Image GenerationCode0
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute ManipulationsCode0
Object-Centric Relational Representations for Image GenerationCode0
CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image SynthesisCode0
Enhancing GAN Performance through Neural Architecture Search and Tensor DecompositionCode0
Image Content Generation with Causal ReasoningCode0
Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank DecompositionCode0
Enhancing Image Generation Fidelity via Progressive PromptsCode0
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large ScaleCode0
Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)Code0
Image Embedding for Denoising Generative ModelsCode0
Diffusion Counterfactual Generation with Semantic AbductionCode0
Semi-supervised Multimodal Representation Learning through a Global WorkspaceCode0
Enhancing Object Coherence in Layout-to-Image SynthesisCode0
BLADERUNNER: Rapid Countermeasure for Synthetic (AI-Generated) StyleGAN FacesCode0
Medical Image Synthesis with Deep Convolutional Adversarial NetworksCode0
Enhancing Quantitative Image Synthesis through Pretraining and Resolution Scaling for Bone Mineral Density Estimation from a Plain X-ray ImageCode0
Medical Imaging Complexity and its Effects on GAN PerformanceCode0
Show:102550
← PrevPage 114 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