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 5701–5750 of 6689 papers

TitleStatusHype
End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure ImagesCode1
MTSS-GAN: Multivariate Time Series Simulation Generative Adversarial NetworksCode1
Searching towards Class-Aware Generators for Conditional Generative Adversarial NetworksCode0
Deep Convolutional GANs for Car Image Generation—0
ContraGAN: Contrastive Learning for Conditional Image Generation—0
Generating Annotated High-Fidelity Images Containing Multiple Coherent ObjectsCode0
Locally Masked Convolution for Autoregressive ModelsCode1
Neural Cellular Automata Manifold—0
Deep Polynomial Neural NetworksCode1
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators—0
A Generative Model for Texture Synthesis based on Optimal Transport between Feature DistributionsCode0
Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis—0
Denoising Diffusion Probabilistic ModelsCode2
Diverse Image Generation via Self-Conditioned GANsCode1
Differentiable Augmentation for Data-Efficient GAN TrainingCode2
Towards a Neural Graphics Pipeline for Controllable Image Generation—0
Auxiliary-task learning for geographic data with autoregressive embeddingsCode1
Progressively Unfreezing Perceptual GAN—0
Multi-Density Sketch-to-Image Translation Network—0
The shape and simplicity biases of adversarially robust ImageNet-trained CNNsCode0
Improved Techniques for Training Score-Based Generative ModelsCode2
DeshuffleGAN: A Self-Supervised GAN to Improve Structure LearningCode0
Improved Conditional Flow Models for Molecule to Image SynthesisCode0
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow ReconstructionCode0
Improving GAN Training with Probability Ratio Clipping and Sample ReweightingCode1
Training Generative Adversarial Networks with Limited DataCode2
Cumulant GAN—0
GANs in computer vision ebookCode1
Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging—0
On Noise Injection in Generative Adversarial NetworksCode3
Explicit Gradient Learning—0
Super-resolution Variational Auto-EncodersCode1
Probabilistic AutoencoderCode1
Reposing Humans by Warping 3D FeaturesCode1
Learning Texture Transformer Network for Image Super-ResolutionCode1
A Robust Attentional Framework for License Plate Recognition in the WildCode0
Structurally aware bidirectional unpaired image to image translation between CT and MR—0
RIT-Eyes: Rendering of near-eye images for eye-tracking applications—0
mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural NetworksCode0
Image Augmentations for GAN Training—0
Nested Scale Editing for Conditional Image Synthesis—0
Transformation GAN for Unsupervised Image Synthesis and Representation Learning—0
CookGAN: Causality Based Text-to-Image Synthesis—0
P-nets: Deep Polynomial Neural NetworksCode1
MISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis—0
Attack to Explain Deep Representation—0
Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas—0
Nested Scale-Editing for Conditional Image Synthesis—0
RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge—0
Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning—0
Show:102550
← PrevPage 115 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