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 5951–6000 of 6689 papers

TitleStatusHype
Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement—0
MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image GenerationCode0
Semantic Hierarchy Emerges in Deep Generative Representations for Scene SynthesisCode0
Fine-grained Synthesis of Unrestricted Adversarial Examples—0
Language-based Colorization of Scene SketchesCode0
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax GameCode0
MMGAN: Generative Adversarial Networks for Multi-Modal Distributions—0
Question-Conditioned Counterfactual Image Generation for VQA—0
A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling—0
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications—0
Collapse Resistant Deep Convolutional GAN for Multi-Object Image Generation—0
Quality Aware Generative Adversarial NetworksCode0
Multi-marginal Wasserstein GANCode1
Self-supervised Deformation Modeling for Facial Expression Editing—0
Pixel-wise Conditioning of Generative Adversarial NetworksCode0
Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Human-Like Sketches—0
Text-to-image synthesis method evaluation based on visual patterns—0
Denoising and Regularization via Exploiting the Structural Bias of Convolutional GeneratorsCode0
Small-GAN: Speeding Up GAN Training Using Core-sets—0
Semantic Object Accuracy for Generative Text-to-Image SynthesisCode0
Consistency Regularization for Generative Adversarial Networks—0
Fair Generative Modeling via Weak SupervisionCode0
Study of Deep Generative Models for Inorganic Chemical CompositionsCode0
TRB: A Novel Triplet Representation for Understanding 2D Human BodyCode0
Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis—0
Bridging the Gap Between f-GANs and Wasserstein GANsCode1
A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis—0
Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)Code0
Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks—0
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation—0
BooVAE: A Scalable Framework for Continual VAE Learning under Boosting Approach—0
Transform the Set: Memory Attentive Generation of Guided and Unguided Image Collages—0
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image SynthesisCode0
Gradient penalty from a maximum margin perspectiveCode0
Image Generation and Recognition (Emotions)—0
Implicit competitive regularization in GANsCode0
Artistic Glyph Image Synthesis via One-Stage Few-Shot LearningCode1
Defending Neural Backdoors via Generative Distribution ModelingCode0
Visual Indeterminacy in GAN Art—0
Prescribed Generative Adversarial NetworksCode1
Text-to-Image Synthesis Based on Machine Generated Captions—0
A Conditional Generative Model for Predicting Material Microstructures from Processing Methods—0
ZeRO: Memory Optimizations Toward Training Trillion Parameter ModelsCode1
Bootstrapping Conditional GANs for Video Game Level Generation—0
Identity From Here, Pose From There: Self-Supervised Disentanglement and Generation of Objects Using Unlabeled Videos—0
VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature PreservationCode0
ClothFlow: A Flow-Based Model for Clothed Person GenerationCode0
Semantics-Enhanced Adversarial Nets for Text-to-Image Synthesis—0
Instance-Guided Context Rendering for Cross-Domain Person Re-Identification—0
FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On—0
Show:102550
← PrevPage 120 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