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 3801–3850 of 6689 papers

TitleStatusHype
An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models—0
UMFuse: Unified Multi View Fusion for Human Editing applications—0
Unbiased General Annotated Dataset Generation—0
When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization—0
Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement—0
not-so-big-GAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution—0
not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution—0
Novel Deep Learning Approach to Derive Cytokeratin Expression and Epithelium Segmentation from DAPI—0
3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance—0
An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levels—0
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment—0
NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment—0
Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation—0
Numerical Pruning for Efficient Autoregressive Models—0
UNCERTAINTY QUANTIFICATION USING VARIATIONAL INFERENCE FOR BIOMEDICAL IMAGE SEGMENTATION—0
Unconditional Scene Graph Generation—0
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis—0
OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes—0
ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation—0
Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control—0
Object-Centric Image Generation from Layouts—0
Object-Centric Image Generation with Factored Depths, Locations, and Appearances—0
Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck—0
Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding—0
Object-level Visual Prompts for Compositional Image Generation—0
Obj-GloVe: Scene-Based Contextual Object Embedding—0
Uncovering Regional Defaults from Photorealistic Forests in Text-to-Image Generation with DALL-E 2—0
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models—0
OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation—0
A Noise is Worth Diffusion Guidance—0
Omni^2: Unifying Omnidirectional Image Generation and Editing in an Omni Model—0
OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction—0
OmniControlNet: Dual-stage Integration for Conditional Image Generation—0
Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image—0
An Introduction to Image Synthesis with Generative Adversarial Nets—0
An Interpretable Generative Model for Handwritten Digit Image Synthesis—0
OmniPrism: Learning Disentangled Visual Concept for Image Generation—0
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model—0
OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understanding—0
An Intermediate Fusion ViT Enables Efficient Text-Image Alignment in Diffusion Models—0
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis—0
On Conditioning GANs to Hierarchical Ontologies—0
On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models—0
An Initial Exploration of Default Images in Text-to-Image Generation—0
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion—0
OneActor: Consistent Character Generation via Cluster-Conditioned Guidance—0
One Communication Round is All It Needs for Federated Fine-Tuning Foundation Models—0
One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications—0
OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering—0
An Improved Method for Personalizing Diffusion Models—0
Show:102550
← PrevPage 77 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