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 3151–3200 of 6689 papers

TitleStatusHype
Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training—0
JoyType: A Robust Design for Multilingual Visual Text Creation—0
Image-guided Neural Object Rendering—0
Image Inpainting Models are Effective Tools for Instruction-guided Image Editing—0
Reconstruct Spine CT from Biplanar X-Rays via Diffusion Learning—0
Geometric Median Matching for Robust k-Subset Selection from Noisy Data—0
Geometric Image Synthesis—0
Imagen Video: High Definition Video Generation with Diffusion Models—0
Geometric Generative Models based on Morphological Equivariant PDEs and GANs—0
Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks—0
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models—0
Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking—0
Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts—0
Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training—0
GeoBiked: A Dataset with Geometric Features and Automated Labeling Techniques to Enable Deep Generative Models in Engineering Design—0
DiffBrush:Just Painting the Art by Your Hands—0
3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation—0
Joint Pose and Expression Modeling for Facial Expression Recognition—0
GenSpace: Benchmarking Spatially-Aware Image Generation—0
Image Super-Resolution With Deep Variational Autoencoders—0
Decoder-Only LLMs are Better Controllers for Diffusion Models—0
GenLit: Reformulating Single-Image Relighting as Video Generation—0
Image Synthesis-based Late Stage Cancer Augmentation and Semi-Supervised Segmentation for MRI Rectal Cancer Staging—0
Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning—0
Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images—0
Decentralized Learning of Generative Adversarial Networks from Non-iid Data—0
Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion model—0
GENHOP: An Image Generation Method Based on Successive Subspace Learning—0
Image Synthesis via Semantic Composition—0
GenFlow: Interactive Modular System for Image Generation—0
Image Synthesis with Class-Aware Semantic Diffusion Models for Surgical Scene Segmentation—0
Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection—0
Deceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations—0
Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation—0
A^3DSegNet: Anatomy-aware artifact disentanglement and segmentation network for unpaired segmentation, artifact reduction, and modality translation—0
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations—0
Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks—0
Generic Perceptual Loss for Modeling Structured Output Dependencies—0
Generic Camera Attribute Control using Bayesian Optimization—0
Beyond Blur: A Fluid Perspective on Generative Diffusion Models—0
Generator Matching: Generative modeling with arbitrary Markov processes—0
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model—0
IMAGINE: Image Synthesis by Image-Guided Model Inversion—0
Imagine yourself: Tuning-Free Personalized Image Generation—0
Generator Born from Classifier—0
Debiasing Counterfactuals In the Presence of Spurious Correlations—0
Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams—0
Differentially Private Diffusion Models Generate Useful Synthetic Images—0
Jointly Trained Image and Video Generation using Residual Vectors—0
Generative Zoo—0
Show:102550
← PrevPage 64 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