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 2951–3000 of 6689 papers

TitleStatusHype
Inverting Adversarially Robust Networks for Image SynthesisCode0
AI-Driven Cytomorphology Image Synthesis for Medical DiagnosticsCode0
Iterative Neural Autoregressive Distribution Estimator NADE-kCode0
The shape and simplicity biases of adversarially robust ImageNet-trained CNNsCode0
Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image GenerationCode0
Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image SynthesisCode0
Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected SituationsCode0
IntroVAE: Introspective Variational Autoencoders for Photographic Image SynthesisCode0
Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability ConnectionCode0
Interpreting Large Text-to-Image Diffusion Models with Dictionary LearningCode0
InvDiff: Invariant Guidance for Bias Mitigation in Diffusion ModelsCode0
Explainable Deep Learning: A Visual Analytics Approach with Transition MatricesCode0
Interferometric Neural NetworksCode0
Expertise elevates AI usage: experimental evidence comparing laypeople and professional artistsCode0
Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait RepresentationsCode0
Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student LearningCode0
Generating Intermediate Representations for Compositional Text-To-Image GenerationCode0
Experimental Quantum Generative Adversarial Networks for Image GenerationCode0
Conditional Wasserstein Distances with Applications in Bayesian OT Flow MatchingCode0
Iterative Neural Autoregressive Distribution Estimator (NADE-k)Code0
Example-Guided Style Consistent Image Synthesis from Semantic LabelingCode0
Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic OptimizationCode0
Instant Photorealistic Neural Radiance Fields StylizationCode0
Instance Normalization: The Missing Ingredient for Fast StylizationCode0
Exact Fusion via Feature Distribution Matching for Few-shot Image GenerationCode0
Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!Code0
Backdooring Bias into Text-to-Image ModelsCode0
Ink removal from histopathology whole slide images by combining classification, detection and image generation modelsCode0
-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite DimensionsCode0
EvoGAN: An Evolutionary Computation Assisted GANCode0
Deformable GANs for Pose-based Human Image GenerationCode0
A High-Quality Robust Diffusion Framework for Corrupted DatasetCode0
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational AutoencodersCode0
High-Resolution Deep Convolutional Generative Adversarial NetworksCode0
Deformation equivariant cross-modality image synthesis with paired non-aligned training dataCode0
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single ImageCode0
Evaluating the Impact of Intensity Normalization on MR Image SynthesisCode0
Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixerCode0
Conditional Image Generation with PixelCNN DecodersCode0
A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning ConventionsCode0
Indonesian Text-to-Image Synthesis with Sentence-BERT and FastGANCode0
Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model TrainingCode0
Learn, Imagine and Create: Text-to-Image Generation from Prior KnowledgeCode0
Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image SynthesisCode0
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal PerspectiveCode0
Improving Fine-Grained Control via Aggregation of Multiple Diffusion ModelsCode0
Improving the Efficiency of Visually Augmented Language ModelsCode0
Improving the Evaluation of Generative Models with Fuzzy LogicCode0
Asymmetric Bias in Text-to-Image Generation with Adversarial AttacksCode0
Improving MMD-GAN Training with Repulsive Loss FunctionCode0
Show:102550
← PrevPage 60 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