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 1351–1400 of 6689 papers

TitleStatusHype
Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models—0
Physics Informed Distillation for Diffusion ModelsCode2
A Survey on Vision Autoregressive Model—0
Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation—0
TIPO: Text to Image with Text Presampling for Prompt OptimizationCode2
Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic Editing—0
Emotion Classification of Children Expressions—0
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution—0
Evaluating the Generation of Spatial Relations in Text and Image Generative Models—0
Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion—0
Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study—0
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image SynthesisCode1
Layout Control and Semantic Guidance with Attention Loss Backward for T2I Diffusion Model—0
Token Merging for Training-Free Semantic Binding in Text-to-Image SynthesisCode2
Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models—0
More Expressive Attention with Negative WeightsCode0
DDIM-Driven Coverless Steganography Scheme with Real Key—0
Region-Aware Text-to-Image Generation via Hard Binding and Soft RefinementCode4
PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation—0
Scalable, Tokenization-Free Diffusion Model Architectures with Efficient Initial Convolution and Fixed-Size Reusable Structures for On-Device Image Generation—0
Autoregressive Models in Vision: A SurveyCode4
Improving image synthesis with diffusion-negative sampling—0
Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models—0
Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation ModelCode0
Conditional Diffusion Model for Longitudinal Medical Image Generation—0
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation—0
Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models—0
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric FinetuningCode0
BendVLM: Test-Time Debiasing of Vision-Language EmbeddingsCode0
Image Understanding Makes for A Good Tokenizer for Image GenerationCode1
Taming Rectified Flow for Inversion and EditingCode4
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation ModelsCode5
SEE-DPO: Self Entropy Enhanced Direct Preference Optimization—0
DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image GenerationCode1
ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks—0
Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation—0
Textual Aesthetics in Large Language ModelsCode0
DiT4Edit: Diffusion Transformer for Image Editing—0
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models—0
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?—0
Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising—0
Training-free Regional Prompting for Diffusion TransformersCode4
Towards Small Object Editing: A Benchmark Dataset and A Training-Free ApproachCode0
DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning—0
DreamPolish: Domain Score Distillation With Progressive Geometry Generation—0
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models—0
Advancements in Data Processing and Calibration for the Hyperspectral Imaging Satellite (HySIS)—0
Generative AI-based Pipeline Architecture for Increasing Training Efficiency in Intelligent Weed Control Systems—0
Evaluation Metric for Quality Control and Generative Models in Histopathology Images—0
Randomized Autoregressive Visual GenerationCode5
Show:102550
← PrevPage 28 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