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 5701–5725 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
Show:102550
← PrevPage 229 of 268Next →
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