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 4301–4350 of 6689 papers

TitleStatusHype
SPIRiT-Diffusion: SPIRiT-driven Score-Based Generative Modeling for Vessel Wall imaging—0
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
The Infinite Index: Information Retrieval on Generative Text-To-Image Models—0
Towards Smooth Video CompositionCode1
3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose MappingCode2
Image Compression with Product Quantized Masked Image Modeling—0
LidarCLIP or: How I Learned to Talk to Point CloudsCode1
Score-based Generative Modeling Secretly Minimizes the Wasserstein DistanceCode1
HACA3: A Unified Approach for Multi-site MR Image Harmonization—0
Towards Practical Plug-and-Play Diffusion ModelsCode1
CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation LearningCode1
The Stable Artist: Steering Semantics in Diffusion Latent SpaceCode2
YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure SegmentationCode1
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow RemovalCode1
Training-Free Structured Diffusion Guidance for Compositional Text-to-Image SynthesisCode2
SmartBrush: Text and Shape Guided Object Inpainting with Diffusion ModelCode0
Album cover art image generation with Generative Adversarial Networks—0
Seeing a Rose in Five Thousand WaysCode1
Shadow Removal by High-Quality Shadow SynthesisCode0
SINE: SINgle Image Editing with Text-to-Image Diffusion ModelsCode1
Ensuring Visual Commonsense Morality for Text-to-Image Generation—0
GLeaD: Improving GANs with A Generator-Leading TaskCode1
Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis—0
Causal Inference via Style Transfer for Out-of-distribution GeneralisationCode1
ADIR: Adaptive Diffusion for Image Reconstruction—0
M-VADER: A Model for Diffusion with Multimodal Context—0
RANA: Relightable Articulated Neural Avatars—0
Semantic-Conditional Diffusion Networks for Image CaptioningCode2
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
QC-StyleGAN -- Quality Controllable Image Generation and ManipulationCode1
Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image SynthesisCode1
3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models—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
SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction—0
Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion ModelsCode1
SGDraw: Scene Graph Drawing Interface Using Object-Oriented RepresentationCode0
Extracting Semantic Knowledge from GANs with Unsupervised Learning—0
3D Neural Field Generation using Triplane Diffusion—0
Dr.3D: Adapting 3D GANs to Artistic Drawings—0
Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders—0
High-Fidelity Guided Image Synthesis with Latent Diffusion Models—0
SinDDM: A Single Image Denoising Diffusion ModelCode1
Dimensionality-Varying Diffusion Process—0
Wavelet Diffusion Models are fast and scalable Image GeneratorsCode2
Refining Generative Process with Discriminator Guidance in Score-based Diffusion ModelsCode1
Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis—0
Show:102550
← PrevPage 87 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