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 6601–6650 of 6689 papers

TitleStatusHype
Calibrating Energy-based Generative Adversarial NetworksCode0
Towards Adversarial Retinal Image SynthesisCode0
Wasserstein GANCode1
Loss-Sensitive Generative Adversarial Networks on Lipschitz DensitiesCode0
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other ModificationsCode1
Image Generation and Editing with Variational Info Generative AdversarialNetworks—0
A General and Adaptive Robust Loss FunctionCode1
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis—0
DeepFace: Face Generation using Deep Learning—0
PixelCNN Models with Auxiliary Variables for Natural Image Modeling—0
Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images—0
Medical Image Synthesis with Context-Aware Generative Adversarial Networks—0
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision—0
Fast Patch-based Style Transfer of Arbitrary StyleCode1
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial NetworksCode0
A Maximum A Posteriori Estimation Framework for Robust High Dynamic Range Video Synthesis—0
Message Passing Multi-Agent GANs—0
Scribbler: Controlling Deep Image Synthesis with Sketch and ColorCode0
Improved Variational Inference with Inverse Autoregressive FlowCode0
Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts—0
Invariant Representations for Noisy Speech Recognition—0
Variational Lossy Autoencoder—0
Unsupervised Cross-Domain Image GenerationCode2
Generative Multi-Adversarial NetworksCode0
Conditional Image Synthesis With Auxiliary Classifier GANsCode1
Professor Forcing: A New Algorithm for Training Recurrent NetworksCode0
Learning What and Where to Draw—0
Rain structure transfer using an exemplar rain image for synthetic rain image generation—0
Example-Based Image Synthesis via Randomized Patch-Matching—0
Neural Photo Editing with Introspective Adversarial NetworksCode0
Generating Synthetic Data for Text RecognitionCode0
Instance Normalization: The Missing Ingredient for Fast StylizationCode0
DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation—0
Interactive Illumination Invariance—0
Generating Images Part by Part with Composite Generative Adversarial Networks—0
Adversarial Training For Sketch Retrieval—0
Conditional Image Generation with PixelCNN DecodersCode0
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial NetsCode1
Improved Techniques for Training GANsCode1
Incorporating long-range consistency in CNN-based texture generationCode1
Adversarially Learned InferenceCode0
Laplacian Patch-Based Image Synthesis—0
Image Style Transfer Using Convolutional Neural NetworksCode0
Density estimation using Real NVPCode1
Generative Adversarial Text to Image SynthesisCode1
Neural Autoregressive Distribution EstimationCode0
Training \& Quality Assessment of an Optical Character Recognition Model for Northern Haida—0
Towards Conceptual CompressionCode0
Pixel-Level Domain TransferCode0
Appearance Harmonization for Single Image Shadow Removal—0
Show:102550
← PrevPage 133 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