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 6401–6450 of 6689 papers

TitleStatusHype
Human Appearance Transfer—0
A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation—0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis—0
Whitening and Coloring batch transform for GANsCode0
Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly DetectionCode0
On GANs and GMMsCode0
On gradient regularizers for MMD GANsCode0
Theory and Experiments on Vector Quantized AutoencodersCode0
Deep Generative Models for Distribution-Preserving Lossy CompressionCode0
Generative Adversarial Image Synthesis with Decision Tree Latent Controller—0
Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss—0
Robust Conditional Generative Adversarial NetworksCode0
Distribution Matching Losses Can Hallucinate Features in Medical Image TranslationCode0
Self-Attention Generative Adversarial NetworksCode1
Turbo Learning for Captionbot and Drawingbot—0
Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks—0
XOGAN: One-to-Many Unsupervised Image-to-Image Translation—0
Normal Similarity Network for Generative Modelling—0
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature DecorationCode0
SPG-Net: Segmentation Prediction and Guidance Network for Image InpaintingCode0
High-resolution medical image synthesis using progressively grown generative adversarial networks—0
ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs—0
MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation—0
Unpaired Multi-Domain Image Generation via Regularized Conditional GANsCode0
Fast-converging Conditional Generative Adversarial Networks for Image Synthesis—0
Transferring GANs: generating images from limited dataCode0
MC-GAN: Multi-conditional Generative Adversarial Network for Image SynthesisCode0
Text to Image Synthesis Using Generative Adversarial Networks—0
Polish Corpus of Annotated Descriptions of Images—0
WikiArt Emotions: An Annotated Dataset of Emotions Evoked by Art—0
Semi-parametric Image SynthesisCode0
Adversarial Training of Variational Auto-encoders for High Fidelity Image GenerationCode0
Synthesizing Images of Humans in Unseen PosesCode0
Cross-Domain Adversarial Auto-EncoderCode0
A Hybrid Model for Identity Obfuscation by Face Replacement—0
A Variational U-Net for Conditional Appearance and Shape GenerationCode0
MelanoGANs: High Resolution Skin Lesion Synthesis with GANs—0
Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI—0
Projection image-to-image translation in hybrid X-ray/MR imaging—0
Nonlinear 3D Face Morphable ModelCode0
View Extrapolation of Human Body from a Single Image—0
Ranking CGANs: Subjective Control over Semantic Image Attributes—0
Modular Generative Adversarial NetworksCode0
Language Modeling with Generative AdversarialNetworks—0
Image Generation from Scene GraphsCode1
Correlated discrete data generation using adversarial training—0
DeSIGN: Design Inspiration from Generative NetworksCode0
Guide Me: Interacting with Deep Networks—0
3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation—0
Image Generation and Translation with Disentangled Representations—0
Show:102550
← PrevPage 129 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