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 3651–3700 of 6689 papers

TitleStatusHype
Chili Pepper Disease Diagnosis via Image Reconstruction Using GrabCut and Generative Adversarial Serial Autoencoder—0
DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation—0
TauPETGen: Text-Conditional Tau PET Image Synthesis Based on Latent Diffusion Models—0
Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera—0
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis—0
Masked Diffusion Models Are Fast Distribution LearnersCode1
Align, Adapt and Inject: Sound-guided Unified Image Generation—0
The Cultivated Practices of Text-to-Image Generation—0
Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning—0
Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text SynthesisCode0
Conditional Text Image Generation with Diffusion Models—0
Graph Self-Supervised Learning for Endoscopic Image MatchingCode0
GD-VDM: Generated Depth for better Diffusion-based Video GenerationCode0
MARBLE: Music Audio Representation Benchmark for Universal EvaluationCode1
Point-Cloud Completion with Pretrained Text-to-image Diffusion ModelsCode1
Referenceless User Controllable Semantic Image SynthesisCode0
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion ModelsCode1
Drag-guided diffusion models for vehicle image generation—0
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map AlignmentCode1
DreamHuman: Animatable 3D Avatars from Text—0
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers—0
Prompt Performance Prediction for Image Generation—0
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image SynthesisCode2
Norm-guided latent space exploration for text-to-image generationCode1
Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image SynthesisCode1
Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned GenerationCode1
On the Robustness of Latent Diffusion ModelsCode1
VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing—0
OT-Net: A Reusable Neural Optimal Transport Solver—0
Perceptions and Realities of Text-to-Image Generation—0
GBSD: Generative Bokeh with Stage Diffusion—0
AniFaceDrawing: Anime Portrait Exploration during Your Sketching—0
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis—0
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment—0
Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model—0
Learning Unnormalized Statistical Models via Compositional Optimization—0
Fill-Up: Balancing Long-Tailed Data with Generative Models—0
AI-Generated Image Detection using a Cross-Attention Enhanced Dual-Stream NetworkCode1
Fast Diffusion ModelCode0
Happy People -- Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models—0
Face0: Instantaneously Conditioning a Text-to-Image Model on a Face—0
Learning Joint Latent Space EBM Prior Model for Multi-layer Generator—0
Image Vectorization: a ReviewCode5
Beyond Surface Statistics: Scene Representations in a Latent Diffusion ModelCode1
Ownership Protection of Generative Adversarial Networks—0
Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces—0
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models—0
Multi-Architecture Multi-Expert Diffusion Models—0
IFaceUV: Intuitive Motion Facial Image Generation by Identity Preservation via UV map—0
Show:102550
← PrevPage 74 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