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
Synthetic dataset generation for object-to-model deep learning in industrial applicationsCode0
Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample FilteringCode0
Neural Autoregressive Distribution EstimationCode0
Generation of Artificial CT Images using Patch-based Conditional Generative Adversarial NetworksCode0
Generation of Indian Sign Language Letters, Numbers, and WordsCode0
Lateralization MLP: A Simple Brain-inspired Architecture for DiffusionCode0
Generative Active Learning for Image Synthesis PersonalizationCode0
Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground TruthCode0
LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption GenerationCode0
Neural Characteristic Function Learning for Conditional Image GenerationCode0
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion ModelsCode0
LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object IntegrationCode0
Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen StyleCode0
USIS: Unsupervised Semantic Image SynthesisCode0
Generative Adversarial Networks: An OverviewCode0
Layered Rendering Diffusion Model for Controllable Zero-Shot Image SynthesisCode0
TextureGAN: Controlling Deep Image Synthesis with Texture PatchesCode0
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion ModellingCode0
Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image GenerationCode0
LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep LearningCode0
Diffusion Sampling with Momentum for Mitigating Divergence ArtifactsCode0
CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image GenerationCode0
Neural Photo Editing with Introspective Adversarial NetworksCode0
Generative Adversarial Networks with Decoder-Encoder Output NoiseCode0
Spectral Normalization for Generative Adversarial NetworksCode0
Neural Scene Decoration from a Single PhotographCode0
Neural Style Transfer for Vector GraphicsCode0
The Role of Data Curation in Image CaptioningCode0
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious CorrelationsCode0
Neural Voxel Renderer: Learning an Accurate and Controllable Rendering ToolCode0
Challenges in Disentangling Independent Factors of VariationCode0
Prompting Diffusion Representations for Cross-Domain Semantic SegmentationCode0
Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 TokensCode0
The Art of Food: Meal Image Synthesis from IngredientsCode0
Disentangling representations of retinal images with generative modelsCode0
CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned NormalizationCode0
PromptMap: An Alternative Interaction Style for AI-Based Image GenerationCode0
LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance RegularizationCode0
Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creationCode0
Character-Centric Story Visualization via Visual Planning and Token AlignmentCode0
LEAD: Min-Max Optimization from a Physical PerspectiveCode0
Background Image Generation Using Boolean OperationsCode0
ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?Code0
Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based ModelsCode0
Learn, Imagine and Create: Text-to-Image Generation from Prior KnowledgeCode0
PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like InteractionsCode0
Contrastive Image Synthesis and Self-supervised Feature Adaptation for Cross-Modality Biomedical Image SegmentationCode0
Enhancing Conditional Image Generation with Explainable Latent Space ManipulationCode0
Scissorhands: Scrub Data Influence via Connection Sensitivity in NetworksCode0
Backdoor Attack is a Devil in Federated GAN-based Medical Image SynthesisCode0
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