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 4651–4700 of 6689 papers

TitleStatusHype
On the Adversarial Robustness of Generative Autoencoders in the Latent Space—0
Training Energy-Based Models with Diffusion Contrastive Divergences—0
Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability ConnectionCode0
AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation—0
Squeezing Large-Scale Diffusion Models for Mobile—0
Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis—0
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance—0
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation—0
Facial Image Generation from Bangla Textual Description using DCGAN and Bangla FastTextCode0
Counting Guidance for High Fidelity Text-to-Image Synthesis—0
Stay on topic with Classifier-Free Guidance—0
CLIPAG: Towards Generator-Free Text-to-Image Generation—0
Approximated Prompt Tuning for Vision-Language Pre-trained Models—0
Semi-supervised Multimodal Representation Learning through a Global WorkspaceCode0
A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis—0
Localized Text-to-Image Generation for Free via Cross Attention Control—0
DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited DataCode0
UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense DisambiguationCode0
A New Paradigm for Generative Adversarial Networks based on Randomized Decision RulesCode0
Zero-shot spatial layout conditioning for text-to-image diffusion models—0
Directional diffusion models for graph representation learning—0
DreamEdit: Subject-driven Image Editing—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
Chili Pepper Disease Diagnosis via Image Reconstruction Using GrabCut and Generative Adversarial Serial Autoencoder—0
The Cultivated Practices of Text-to-Image Generation—0
Align, Adapt and Inject: Sound-guided Unified Image Generation—0
Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning—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
Conditional Text Image Generation with Diffusion Models—0
Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text SynthesisCode0
GD-VDM: Generated Depth for better Diffusion-based Video GenerationCode0
Graph Self-Supervised Learning for Endoscopic Image MatchingCode0
Referenceless User Controllable Semantic Image SynthesisCode0
Drag-guided diffusion models for vehicle image generation—0
Prompt Performance Prediction for Image Generation—0
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers—0
DreamHuman: Animatable 3D Avatars from Text—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
VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing—0
Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model—0
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis—0
AniFaceDrawing: Anime Portrait Exploration during Your Sketching—0
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment—0
Learning Unnormalized Statistical Models via Compositional Optimization—0
Fast Diffusion ModelCode0
Fill-Up: Balancing Long-Tailed Data with Generative Models—0
Show:102550
← PrevPage 94 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