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 1901–1950 of 6689 papers

TitleStatusHype
Learning to Generate Levels From NothingCode1
Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNNCode1
Fully Spiking Denoising Diffusion Implicit ModelsCode1
Full-Glow: Fully conditional Glow for more realistic image generationCode1
ClimateGAN: Raising Climate Change Awareness by Generating Images of FloodsCode1
Causal Inference via Style Transfer for Out-of-distribution GeneralisationCode1
CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationCode1
Fully Spiking Variational AutoencoderCode1
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style TransferCode1
Taming Transformers for High-Resolution Image SynthesisCode1
From Face to Natural Image: Learning Real Degradation for Blind Image Super-ResolutionCode1
From Image to Imuge: Immunized Image GenerationCode1
CLIP-Diffusion-LM: Apply Diffusion Model on Image CaptioningCode1
Frido: Feature Pyramid Diffusion for Complex Scene Image SynthesisCode1
CLIP-Forge: Towards Zero-Shot Text-to-Shape GenerationCode1
Conditional Image Synthesis With Auxiliary Classifier GANsCode1
Conditional Image Generation with Score-Based Diffusion ModelsCode1
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIPCode1
Generating Diverse High-Fidelity Images with VQ-VAE-2Code1
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANsCode1
ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram DigitizationCode1
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANsCode1
Frequency Domain Image Translation: More Photo-realistic, Better Identity-preservingCode1
GAN-Control: Explicitly Controllable GANsCode1
Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End PipelineCode1
DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan DesignCode1
Conditional Image Generation and Manipulation for User-Specified ContentCode1
Frame Interpolation with Consecutive Brownian Bridge DiffusionCode1
FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic DataCode1
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningCode1
FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded SamplingCode1
Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion ModelsCode1
ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image DetectionCode1
Dual Contrastive Loss and Attention for GANsCode1
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability VolumesCode1
ForkGAN: Seeing into the Rainy NightCode1
A Cheaper and Better Diffusion Language Model with Soft-Masked NoiseCode1
Dual-Domain Image Synthesis using Segmentation-Guided GANCode1
Foreground-Background Separation through Concept Distillation from Generative Image Foundation ModelsCode1
Forward-only Diffusion Probabilistic ModelsCode1
The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA dataCode1
The Emergence of Reproducibility and Generalizability in Diffusion ModelsCode1
Conditional Diffusion Models for Weakly Supervised Medical Image SegmentationCode1
Dual Pyramid Generative Adversarial Networks for Semantic Image SynthesisCode1
Focal Frequency Loss for Image Reconstruction and SynthesisCode1
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingCode1
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image GenerationCode1
Things not Written in Text: Exploring Spatial Commonsense from Visual SignalsCode1
A Characteristic Function Approach to Deep Implicit Generative ModelingCode1
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image GenerationCode1
Show:102550
← PrevPage 39 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