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 1501–1550 of 6689 papers

TitleStatusHype
Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect DetectionCode1
Edge-preserving noise for diffusion modelsCode1
Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image DetectionCode1
Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image SynthesisCode1
Denoising Diffusion Autoencoders are Unified Self-supervised LearnersCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
Edge Guided GANs with Contrastive Learning for Semantic Image SynthesisCode1
Lessons Learned from the Training of GANs on Artificial DatasetsCode1
LFS-GAN: Lifelong Few-Shot Image GenerationCode1
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion ModelCode1
Learning Self-Consistency for Deepfake DetectionCode1
Aligning Latent and Image Spaces to Connect the UnconnectableCode1
Learning to Manipulate Artistic ImagesCode1
Denoising Likelihood Score Matching for Conditional Score-based Data GenerationCode1
Learning to Sample Effective and Diverse Prompts for Text-to-Image GenerationCode1
Controlling Style and Semantics in Weakly-Supervised Image GenerationCode1
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial TrainingCode1
A Complete Recipe for Diffusion Generative ModelsCode1
Controlling Geometric Abstraction and Texture for Artistic ImagesCode1
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionCode1
Dense Pixel-to-Pixel Harmonization via Continuous Image RepresentationCode1
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANsCode1
Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited MemoryCode1
Density estimation using Real NVPCode1
A disentangled generative model for disease decomposition in chest X-rays via normal image synthesisCode1
Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image SynthesisCode1
Learning to See by Looking at NoiseCode1
Learning Semantic-aware Normalization for Generative Adversarial NetworksCode1
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry ImagesCode1
Generative Modeling with Optimal Transport MapsCode1
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based DecodingCode1
DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion DelineationCode1
Learning Semantic Person Image Generation by Region-Adaptive NormalizationCode1
Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese DishesCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image GenerationCode1
Efficient Feature Extraction for High-resolution Video Frame InterpolationCode1
Learning Texture Transformer Network for Image Super-ResolutionCode1
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar ReconstructionCode1
A Unified Agentic Framework for Evaluating Conditional Image GenerationCode1
A U-Net Based Discriminator for Generative Adversarial NetworksCode1
Generator Knows What Discriminator Should Learn in Unconditional GANsCode1
Controllable Person Image Synthesis with Spatially-Adaptive Warped NormalizationCode1
DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency ModelCode1
GENIE: Higher-Order Denoising Diffusion SolversCode1
Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationCode1
Learning to Discretize Denoising Diffusion ODEsCode1
Learning Two-Stream CNN for Multi-Modal Age-related Macular Degeneration CategorizationCode1
Controllable Person Image Synthesis with Attribute-Decomposed GANCode1
Interactive Character Control with Auto-Regressive Motion Diffusion ModelsCode1
Show:102550
← PrevPage 31 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