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 5351–5400 of 6689 papers

TitleStatusHype
Watermark Faker: Towards Forgery of Digital Image WatermarkingCode1
SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms—0
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC_4Net—0
Context-Aware Layout to Image Generation with Enhanced Object AppearanceCode1
Generation and Simulation of Yeast Microscopy Imagery with Deep Learning—0
Progressive and Aligned Pose Attention Transfer for Person Image GenerationCode1
Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous VariableCode0
Carton dataset synthesis method for domain shift based on foreground texture decoupling and replacementCode0
Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning—0
Generic Perceptual Loss for Modeling Structured Output Dependencies—0
Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets—0
Deep Learning for Chest X-ray Analysis: A Survey—0
Assessment of image generation by quantum annealer—0
Deep Consensus Learning—0
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial NetworkCode1
Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial NetworksCode0
Unsupervised Image Transformation Learning via Generative Adversarial Networks—0
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement—0
HumanGAN: A Generative Model of Humans Images—0
Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-LocalizationCode1
Diverse Semantic Image Synthesis via Probability Distribution ModelingCode1
BIKED: A Dataset for Computational Bicycle Design with Machine Learning BenchmarksCode1
Spectral Tensor Train Parameterization of Deep Learning LayersCode1
Repurposing GANs for One-shot Semantic Part SegmentationCode1
PISE: Person Image Synthesis and Editing with Decoupled GANCode1
Robustness Evaluation of Stacked Generative Adversarial Networks using Metamorphic Testing—0
Anycost GANs for Interactive Image Synthesis and EditingCode1
MOGAN: Morphologic-structure-aware Generative Learning from a Single ImageCode1
Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks—0
Geometry-Guided Street-View Panorama Synthesis from Satellite ImageryCode1
Generative Adversarial TransformersCode2
M6: A Chinese Multimodal Pretrainer—0
Training Generative Adversarial Networks in One StageCode1
Energy-based Models for Earth Observation Applications—0
Conditional Image Generation by Conditioning Variational Auto-EncodersCode1
Zero-Shot Text-to-Image GenerationCode3
Histo-fetch -- On-the-fly processing of gigapixel whole slide images simplifies and speeds neural network trainingCode1
Uncertainty-aware Generalized Adaptive CycleGANCode1
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution HeterogeneityCode1
Style and Pose Control for Image Synthesis of Humans from a Single Monocular View—0
Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory—0
Pose Guided Person Image Generation with Hidden p-Norm Regression—0
Improved Denoising Diffusion Probabilistic ModelsCode3
Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks—0
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative ModelsCode1
Evolving GAN Formulations for Higher Quality Image Synthesis—0
Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation—0
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale UpCode1
Efficient Conditional GAN Transfer with Knowledge Propagation across ClassesCode1
SWAGAN: A Style-based Wavelet-driven Generative ModelCode1
Show:102550
← PrevPage 108 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