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 4051–4100 of 6689 papers

TitleStatusHype
Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback—0
A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressions—0
WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space—0
3D-aware Image Generation and Editing with Multi-modal Conditions—0
PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models—0
A multi-stage GAN for multi-organ chest X-ray image generation and segmentation—0
Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN—0
A Multimodal Visual Encoding Model Aided by Introducing Verbal Semantic Information—0
Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation—0
Plug-and-Play Context Feature Reuse for Efficient Masked Generation—0
Plug-and-Play Controllable Generation for Discrete Masked Models—0
Plug-and-Play Diffusion Distillation—0
A multi-channel cycleGAN for CBCT to CT synthesis—0
Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control—0
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics—0
Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation—0
POEM: Precise Object-level Editing via MLLM control—0
Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry—0
POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation—0
PO-Flow: Flow-based Generative Models for Sampling Potential Outcomes and Counterfactuals—0
PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation—0
PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation—0
3D-Aware Generative Model for Improved Side-View Image Synthesis—0
Point-Driven Interactive Text and Image Layer Editing Using Diffusion Models—0
PointT2I: LLM-based text-to-image generation via keypoints—0
Poisson Flow Joint Model for Multiphase contrast-enhanced CT—0
Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis—0
WMAdapter: Adding WaterMark Control to Latent Diffusion Models—0
Universality of parametric Coupling Flows over parametric diffeomorphisms—0
Polish Corpus of Annotated Descriptions of Images—0
UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing—0
Ponder: Point Cloud Pre-training via Neural Rendering—0
Amora: Black-box Adversarial Morphing Attack—0
pOps: Photo-Inspired Diffusion Operators—0
PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization—0
Pose-driven Attention-guided Image Generation for Person Re-Identification—0
PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation—0
Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networks—0
Pose Guided Fashion Image Synthesis Using Deep Generative Model—0
Pose-Guided Fine-Grained Sign Language Video Generation—0
Pose-guided Generative Adversarial Net for Novel View Action Synthesis—0
Pose Guided Human Image Synthesis with Partially Decoupled GAN—0
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction—0
Pose Guided Person Image Generation with Hidden p-Norm Regression—0
A Modular Open Source Framework for Genomic Variant Calling—0
Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN—0
Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data—0
Posterior Mean Matching: Generative Modeling through Online Bayesian Inference—0
Posterior Promoted GAN With Distribution Discriminator for Unsupervised Image Synthesis—0
PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering—0
Show:102550
← PrevPage 82 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