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 3901–3950 of 6689 papers

TitleStatusHype
Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human MattingCode0
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data—0
Model-Agnostic Human Preference Inversion in Diffusion Models—0
Convergence of Continuous Normalizing Flows for Learning Probability Distributions—0
IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions—0
GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation—0
CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned NormalizationCode0
MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text—0
Grid Diffusion Models for Text-to-Video Generation—0
Dependability Evaluation of Stable Diffusion with Soft Errors on the Model Parameters—0
FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models—0
FairRAG: Fair Human Generation via Fair Retrieval Augmentation—0
Explainable Deep Learning: A Visual Analytics Approach with Transition MatricesCode0
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation—0
Frame by Familiar Frame: Understanding Replication in Video Diffusion Models—0
GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models—0
Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographs—0
CLoRA: A Contrastive Approach to Compose Multiple LoRA Models—0
Detecting Origin Attribution for Text-to-Image Diffusion ModelsCode0
Imperceptible Protection against Style Imitation from Diffusion Models—0
QNCD: Quantization Noise Correction for Diffusion ModelsCode0
Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative ModelsCode0
U-Sketch: An Efficient Approach for Sketch to Image Diffusion Models—0
CPR: Retrieval Augmented Generation for Copyright Protection—0
Conditional Wasserstein Distances with Applications in Bayesian OT Flow MatchingCode0
TextCraftor: Your Text Encoder Can be Image Quality Controller—0
ECNet: Effective Controllable Text-to-Image Diffusion Models—0
Tutorial on Diffusion Models for Imaging and Vision—0
Boosting Diffusion Models with Moving Average Sampling in Frequency Domain—0
CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation—0
Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases—0
SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer—0
Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation—0
Enhancing Neural Network Representations with Prior Knowledge-Based NormalizationCode0
DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment—0
An Intermediate Fusion ViT Enables Efficient Text-Image Alignment in Diffusion Models—0
Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidance—0
Skews in the Phenomenon Space Hinder Generalization in Text-to-Image GenerationCode0
Iso-Diffusion: Improving Diffusion Probabilistic Models Using the Isotropy of the Additive Gaussian Noise—0
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation—0
Multi-Scale Texture Loss for CT denoising with GANsCode0
R3CD: Scene Graph to Image Generation with Relation-aware Compositional Contrastive Control Diffusion—0
Advanced Feature Manipulation for Enhanced Change Detection Leveraging Natural Language Models—0
Geometric Generative Models based on Morphological Equivariant PDEs and GANs—0
Generative Active Learning for Image Synthesis PersonalizationCode0
Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information—0
MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration—0
Analysing Diffusion Segmentation for Medical Images—0
QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping—0
Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation—0
Show:102550
← PrevPage 79 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