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 5051–5100 of 6689 papers

TitleStatusHype
Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis—0
ADIR: Adaptive Diffusion for Image Reconstruction—0
RANA: Relightable Articulated Neural Avatars—0
M-VADER: A Model for Diffusion with Multimodal Context—0
Audio Latent Space Cartography—0
MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain—0
A Domain-specific Perceptual Metric via Contrastive Self-supervised Representation: Applications on Natural and Medical Images—0
Discovering Class-Specific GAN Controls for Semantic Image Synthesis—0
3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models—0
SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction—0
Deep neural network techniques for monaural speech enhancement: state of the art analysis—0
Weakly Supervised Annotations for Multi-modal Greeting Cards Dataset—0
Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders—0
3D Neural Field Generation using Triplane Diffusion—0
SGDraw: Scene Graph Drawing Interface Using Object-Oriented RepresentationCode0
High-Fidelity Guided Image Synthesis with Latent Diffusion Models—0
Extracting Semantic Knowledge from GANs with Unsupervised Learning—0
Dr.3D: Adapting 3D GANs to Artistic Drawings—0
Dimensionality-Varying Diffusion Process—0
The Myth of Culturally Agnostic AI Models—0
Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis—0
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs—0
Hand-Object Interaction Image Generation—0
Conditional Progressive Generative Adversarial Network for satellite image generation—0
Diffusion Probabilistic Model Made Slim—0
Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs—0
Cross-domain Microscopy Cell Counting by Disentangled Transfer Learning—0
Efficient Video Prediction via Sparsely Conditioned Flow Matching—0
Unifying conditional and unconditional semantic image synthesis with OCO-GAN—0
SpaText: Spatio-Textual Representation for Controllable Image Generation—0
Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image—0
ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background SegmentationCode0
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions—0
More comprehensive facial inversion for more effective expression recognitionCode0
ReCo: Region-Controlled Text-to-Image Generation—0
CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields—0
Retrieval-Augmented Multimodal Language Modeling—0
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark—0
Rethinking Implicit Neural Representations for Vision Learners—0
SceneComposer: Any-Level Semantic Image Synthesis—0
VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models—0
DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter—0
TimbreCLIP: Connecting Timbre to Text and Images—0
Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images—0
IC3D: Image-Conditioned 3D Diffusion for Shape Generation—0
Single Stage Multi-Pose Virtual Try-On—0
Potential Auto-driving Threat: Universal Rain-removal Attack—0
UMFuse: Unified Multi View Fusion for Human Editing applications—0
A Creative Industry Image Generation Dataset Based on Captions—0
Will Large-scale Generative Models Corrupt Future Datasets?Code0
Show:102550
← PrevPage 102 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