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 5301–5350 of 6689 papers

TitleStatusHype
Principal Component Density Estimation for Scenario Generation Using Normalizing Flows—0
Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning RepresentationCode0
GENESIS-V2: Inferring Unordered Object Representations without Iterative RefinementCode1
Quaternion Generative Adversarial NetworksCode1
Coarse-to-Fine Searching for Efficient Generative Adversarial Networks—0
Towards Open-World Text-Guided Face Image Generation and ManipulationCode1
The Intrinsic Dimension of Images and Its Impact on LearningCode1
Spectrogram Inpainting for Interactive Generation of Instrument SoundsCode1
Image Super-Resolution via Iterative RefinementCode1
StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis—0
HoughNet: Integrating near and long-range evidence for visual detectionCode1
Learning Semantic Person Image Generation by Region-Adaptive NormalizationCode1
Aligning Latent and Image Spaces to Connect the UnconnectableCode1
VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision TransformersCode0
Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit EditingCode1
IMAGINE: Image Synthesis by Image-Guided Model Inversion—0
Few-shot Image Generation via Cross-domain CorrespondenceCode1
Automatic Correction of Internal Units in Generative Neural Networks—0
Multi-View Image-to-Image Translation Supervised by 3D PoseCode0
Pose Invariant Person Re-Identification using Robust Pose-transformation GANCode0
SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation—0
CoPE: Conditional image generation using Polynomial ExpansionsCode0
MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image SynthesisCode1
Neural RGB-D Surface ReconstructionCode1
InfinityGAN: Towards Infinite-Pixel Image SynthesisCode1
Re-designing cities with conditional adversarial networks—0
Handwriting TransformersCode1
Regularizing Generative Adversarial Networks under Limited DataCode1
Noise Estimation for Generative Diffusion Models—0
Content-Aware GAN CompressionCode1
ReStyle: A Residual-Based StyleGAN Encoder via Iterative RefinementCode2
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable DirectionsCode1
Partition-Guided GANsCode1
Exploiting Relationship for Complex-scene Image Generation—0
Text to Image Generation with Semantic-Spatial Aware GANCode1
Improved Image Generation via Sparse Modeling—0
CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields—0
Dual Contrastive Loss and Attention for GANsCode1
Multi-Class Multi-Instance Count Conditioned Adversarial Image GenerationCode0
Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and TranslationCode1
Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition—0
Photoacoustic image synthesis with generative adversarial networks—0
PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier—0
LatentKeypointGAN: Controlling Images via Latent KeypointsCode0
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative ModelsCode1
Few-shot Semantic Image Synthesis Using StyleGAN PriorCode1
Modeling the Nonsmoothness of Modern Neural Networks—0
Few-Shot Human Motion Transfer by Personalized Geometry and Texture ModelingCode1
AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and StyleCode0
Generating Novel Scene Compositions from Single Images and VideosCode1
Show:102550
← PrevPage 107 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