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 6251–6300 of 6689 papers

TitleStatusHype
Conditional Adversarial Generative Flow for Controllable Image Synthesis—0
Constrained Generative Adversarial Networks for Interactive Image Generation—0
Semantics Disentangling for Text-to-Image Generation—0
HoloGAN: Unsupervised learning of 3D representations from natural imagesCode0
GAN You Do the GAN GAN?Code0
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models—0
Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment—0
COCO-GAN: Generation by Parts via Conditional CoordinatingCode0
Exposing GAN-synthesized Faces Using Landmark Locations—0
Training Object Detectors on Synthetic Images Containing Reflecting Materials—0
Generating Diverse High-Resolution Images with VQ-VAE—0
Auto-Embedding Generative Adversarial Networks for High Resolution Image SynthesisCode0
HYPE: Human-eYe Perceptual Evaluation of Generative Models—0
Deep Generative Models for Generating Labeled Graphs—0
Parallel Recurrent Data Augmentation for GAN training with Limited and Diverse Data—0
Unconstrained Facial Action Unit Detection via Latent Feature DomainCode0
Heuristics for Image Generation from Scene Graphs—0
Lemotif: An Affective Visual Journal Using Deep Neural NetworksCode0
Generate What You Can't See - a View-dependent Image Generation—0
MSG-GAN: Multi-Scale Gradients for Generative Adversarial NetworksCode0
MirrorGAN: Learning Text-to-image Generation by RedescriptionCode0
Voice command generation using Progressive Wavegans—0
Mode Seeking Generative Adversarial Networks for Diverse Image SynthesisCode0
Video Generation from Single Semantic Label MapCode0
LumiPath -- Towards Real-time Physically-based Rendering on Embedded DevicesCode0
Reference-based Variational Autoencoders—0
Adversarial Out-domain Examples for Generative ModelsCode0
Attack Type Agnostic Perceptual Enhancement of Adversarial Images—0
DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis—0
High-Fidelity Image Generation With Fewer Labels—0
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model—0
Object-driven Text-to-Image Synthesis via Adversarial TrainingCode0
Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation—0
Anomaly Detection with Adversarial Dual AutoencodersCode0
Fully-Featured Attribute Transfer—0
Adversarially Approximated Autoencoder for Image Generation and Manipulation—0
Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images—0
Unpriortized Autoencoder For Image Generation—0
Synthesizing New Retinal Symptom Images by Multiple Generative ModelsCode0
Photorealistic Image Synthesis for Object Instance Detection—0
Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning—0
Active Image Synthesis for Efficient Labeling—0
Realistic Image Generation using Region-phrase Attention—0
Compatible and Diverse Fashion Image Inpainting—0
Collaborative Sampling in Generative Adversarial NetworksCode0
A Layer-Based Sequential Framework for Scene Generation with GANsCode0
TF-Replicator: Distributed Machine Learning for ResearchersCode0
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture DesignCode0
Diversity Regularized Adversarial Learning—0
Emerging Convolutions for Generative Normalizing FlowsCode0
Show:102550
← PrevPage 126 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