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 1451–1500 of 6689 papers

TitleStatusHype
Medical Imaging Complexity and its Effects on GAN PerformanceCode0
Deep Generative Models for 3D Medical Image Synthesis—0
Longitudinal Causal Image SynthesisCode0
Scalable Ranked Preference Optimization for Text-to-Image Generation—0
FreeVS: Generative View Synthesis on Free Driving Trajectory—0
A Wavelet Diffusion GAN for Image Super-Resolution—0
Offline Evaluation of Set-Based Text-to-Image GenerationCode0
Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting—0
Hierarchical Clustering for Conditional Diffusion in Image GenerationCode1
MPDS: A Movie Posters Dataset for Image Generation with Diffusion Model—0
IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age TransformationCode0
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization—0
Altogether: Image Captioning via Re-aligning Alt-text—0
Continuous Speech Synthesis using per-token Latent Diffusion—0
Elucidating the design space of language models for image generationCode1
MedDiff-FM: A Diffusion-based Foundation Model for Versatile Medical Image Applications—0
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One StepCode2
SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningCode2
On the Wasserstein Convergence and Straightness of Rectified FlowCode0
SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection—0
Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion—0
Truncated Consistency Models—0
Personalized Image Generation with Large Multimodal ModelsCode1
FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models—0
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation CapabilitiesCode2
Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing FlowsCode0
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image GenerationCode2
Assessing Open-world Forgetting in Generative Image Model Customization—0
CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks—0
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion ModelCode3
ARKit LabelMaker: A New Scale for Indoor 3D Scene UnderstandingCode2
GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction—0
LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-TuningCode0
Fundus to Fluorescein Angiography Video Generation as a Retinal Generative Foundation Model—0
PUMA: Empowering Unified MLLM with Multi-granular Visual GenerationCode2
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models—0
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided DiffusionCode1
Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with MomentumCode0
Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language ConditioningCode0
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous TokensCode2
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-GuidanceCode1
Stable Diffusion with Continuous-time Neural Network—0
On the Relation Between Linear Diffusion and Power Iteration—0
Facing Identity: The Formation and Performance of Identity via Face-Based Artificial Intelligence Technologies—0
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified PerspectiveCode2
FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization—0
Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value OptimizationCode1
3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image GenerationCode3
Evaluating Utility of Memory Efficient Medical Image Generation: A Study on Lung Nodule Segmentation—0
DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks—0
Show:102550
← PrevPage 30 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