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 5501–5550 of 6689 papers

TitleStatusHype
CloTH-VTON: Clothing Three-dimensional reconstruction for Hybrid image-based Virtual Try-ON—0
S2FGAN: Semantically Aware Interactive Sketch-to-Face TranslationCode1
Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive EvaluationCode1
Learning geometry-image representation for 3D point cloud generation—0
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANsCode1
Frequency Domain Image Translation: More Photo-realistic, Better Identity-preservingCode1
Tractable loss function and color image generation of multinary restricted Boltzmann machine—0
Image Generators with Conditionally-Independent Pixel SynthesisCode1
Omni-GAN: On the Secrets of cGANs and BeyondCode1
Adaptive Multiplane Image Generation from a Single Internet Picture—0
Score-Based Generative Modeling through Stochastic Differential EquationsCode1
Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation—0
Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample—0
Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis—0
StyleSpace Analysis: Disentangled Controls for StyleGAN Image GenerationCode2
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature FieldsCode2
Adversarial Generation of Continuous ImagesCode1
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color HistogramsCode1
Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster DataCode1
Generative Adversarial Stacked Autoencoders—0
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on ImagesCode1
Dual Contradistinctive Generative Autoencoder—0
Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?—0
Liquid Warping GAN with Attention: A Unified Framework for Human Image SynthesisCode2
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image GenerationCode1
Cycle-Consistent Generative Rendering for 2D-3D Modality TranslationCode0
Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input MechanismsCode1
Survey2Survey: A deep learning generative model approach for cross-survey image mapping—0
(f,Γ)-Divergences: Interpolating between f-Divergences and Integral Probability Metrics—0
Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning—0
Using GANs to Synthesise Minimum Training Data for Deepfake Generation—0
Two-Stream Appearance Transfer Network for Person Image Generation—0
DeepCFL: Deep Contextual Features Learning from a Single Image—0
Text-to-Image Generation Grounded by Fine-Grained User AttentionCode1
Blind Motion Deblurring through SinGAN Architecture—0
DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation—0
Towards Disentangling Latent Space for Unsupervised Semantic Face EditingCode1
Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework—0
CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute EditingCode1
Exploring DeshuffleGANs in Self-Supervised Generative Adversarial NetworksCode0
Creating cloud-free satellite imagery from image time series with deep learning—0
ControlVAE: Tuning, Analytical Properties, and Performance AnalysisCode4
Enhanced Balancing GAN: Minority-class Image GenerationCode1
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed ImagesCode0
MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait EditingCode1
Maximum a posteriori signal recovery for optical coherence tomography angiography image generation and denoising—0
Leveraging Visual Question Answering to Improve Text-to-Image Synthesis—0
Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks—0
LEAD: Min-Max Optimization from a Physical PerspectiveCode0
Autoregressive Score Matching—0
Show:102550
← PrevPage 111 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