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 5251–5300 of 6689 papers

TitleStatusHype
CAFLOW: Conditional Autoregressive Flows—0
The Image Local Autoregressive TransformerCode1
Semantic Palette: Guiding Scene Generation with Class ProportionsCode1
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 BenchmarkCode1
Multiresolution Equivariant Graph Variational AutoencoderCode1
GANs Can Play Lottery Tickets TooCode1
Controllable Person Image Synthesis with Spatially-Adaptive Warped NormalizationCode1
Consistency Regularization for Variational Auto-EncodersCode0
Cascaded Diffusion Models for High Fidelity Image Generation—0
M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers—0
Gotta Go Fast When Generating Data with Score-Based ModelsCode1
NViSII: A Scriptable Tool for Photorealistic Image GenerationCode1
Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-NetCode1
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingCode1
Pattern Detection in the Activation Space for Identifying Synthesized Content—0
CogView: Mastering Text-to-Image Generation via TransformersCode2
Texture synthesis via projection onto multiscale, multilayer statistics—0
UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis—0
Scatterbrain: Unifying Sparse and Low-rank AttentionCode1
Combining Transformer Generators with Convolutional Discriminators—0
Improving Generation and Evaluation of Visual Stories via Semantic ConsistencyCode1
BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth ImageCode1
Simple Transparent Adversarial Examples—0
Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations—0
Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks—0
Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain AdaptationCode0
ExSinGAN: Learning an Explainable Generative Model from a Single Image—0
NeuroGen: activation optimized image synthesis for discovery neuroscienceCode1
SA-GAN: Structure-Aware GAN for Organ-Preserving Synthetic CT Generation—0
PassFlow: Guessing Passwords with Generative Flows—0
TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets—0
GAN Prior Embedded Network for Blind Face Restoration in the WildCode2
Directional GAN: A Novel Conditioning Strategy for Generative Networks—0
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference—0
GANs for Medical Image Synthesis: An Empirical Study—0
Diffusion Models Beat GANs on Image SynthesisCode2
CASIA-Face-Africa: A Large-scale African Face Image Database—0
Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesis—0
Fast Adaptive Meta-Learning for Few-Shot Image GenerationCode0
Perceptual Gradient NetworksCode0
PD-GAN: Probabilistic Diverse GAN for Image InpaintingCode1
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for GAN Evaluation—0
Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis—0
Pose-driven Attention-guided Image Generation for Person Re-Identification—0
CAGAN: Text-To-Image Generation with Combined Attention GANs—0
EigenGAN: Layer-Wise Eigen-Learning for GANsCode1
Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection—0
On Aliased Resizing and Surprising Subtleties in GAN EvaluationCode2
Voice2Mesh: Cross-Modal 3D Face Model Generation from VoicesCode1
Show:102550
← PrevPage 106 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