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 2451–2500 of 6689 papers

TitleStatusHype
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-OnCode2
Action Detection via an Image Diffusion Process—0
Condition-Aware Neural Network for Controlled Image Generation—0
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data—0
Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation—0
CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned NormalizationCode0
Convergence of Continuous Normalizing Flows for Learning Probability Distributions—0
GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation—0
Towards Realistic Scene Generation with LiDAR Diffusion ModelsCode3
IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions—0
MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text—0
Grid Diffusion Models for Text-to-Video Generation—0
LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented DiffusionCode2
Dependability Evaluation of Stable Diffusion with Soft Errors on the Model Parameters—0
Explainable Deep Learning: A Visual Analytics Approach with Transition MatricesCode0
SCINeRF: Neural Radiance Fields from a Snapshot Compressive ImageCode1
Benchmarking Counterfactual Image GenerationCode1
FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models—0
FairRAG: Fair Human Generation via Fair Retrieval Augmentation—0
CLoRA: A Contrastive Approach to Compose Multiple LoRA Models—0
Imperceptible Protection against Style Imitation from Diffusion Models—0
GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models—0
Detecting Origin Attribution for Text-to-Image Diffusion ModelsCode0
Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographs—0
Vision-Language Synthetic Data Enhances Echocardiography Downstream TasksCode1
Frame by Familiar Frame: Understanding Replication in Video Diffusion Models—0
Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative ModelsCode0
QNCD: Quantization Noise Correction for Diffusion ModelsCode0
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation—0
TextCraftor: Your Text Encoder Can be Image Quality Controller—0
Capability-aware Prompt Reformulation Learning for Text-to-Image GenerationCode1
CPR: Retrieval Augmented Generation for Copyright Protection—0
ECNet: Effective Controllable Text-to-Image Diffusion Models—0
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery AnalysisCode1
Attention Calibration for Disentangled Text-to-Image PersonalizationCode2
U-Sketch: An Efficient Approach for Sketch to Image Diffusion Models—0
Conditional Wasserstein Distances with Applications in Bayesian OT Flow MatchingCode0
Ship in Sight: Diffusion Models for Ship-Image Super ResolutionCode1
Tutorial on Diffusion Models for Imaging and Vision—0
Bidirectional Consistency ModelsCode1
LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image DetectionCode2
Boosting Diffusion Models with Moving Average Sampling in Frequency Domain—0
CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation—0
Self-Rectifying Diffusion Sampling with Perturbed-Attention GuidanceCode3
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation—0
Enhancing Neural Network Representations with Prior Knowledge-Based NormalizationCode0
DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment—0
Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases—0
Iso-Diffusion: Improving Diffusion Probabilistic Models Using the Isotropy of the Additive Gaussian Noise—0
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image GenerationCode2
Show:102550
← PrevPage 50 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