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
SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis—0
Generating images of rare concepts using pre-trained diffusion modelsCode1
IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers—0
DiffuseExpand: Expanding dataset for 2D medical image segmentation using diffusion modelsCode1
TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional GenerationCode1
Single-View Height Estimation with Conditional Diffusion Probabilistic Models—0
Tensor Decomposition for Model Reduction in Neural Networks: A Review—0
Training-Free Location-Aware Text-to-Image Synthesis—0
Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation—0
Controllable Image Generation via Collage Representations—0
Quantitative analysis of collagen remodeling in pancreatic lesions using computationally translated collagen images derived from brightfield microscopy images—0
Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantificationCode1
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement LearningCode1
GlyphDiffusion: Text Generation as Image Generation—0
Exploring Compositional Visual Generation with Latent Classifier Guidance—0
Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation—0
Dehazing-NeRF: Neural Radiance Fields from Hazy Images—0
Persistently Trained, Diffusion-assisted Energy-based ModelsCode0
DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase—0
Using Text-to-Image Generation for Architectural Design Ideation—0
FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits—0
Adaptive Consensus Optimization Method for GANsCode0
DCN-T: Dual Context Network with Transformer for Hyperspectral Image ClassificationCode1
ReelFramer: Human-AI Co-Creation for News-to-Video Translation—0
Look ATME: The Discriminator Mean Entropy Needs AttentionCode1
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion ModelsCode1
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose TransferCode1
Modulating human brain responses via optimal natural image selection and synthetic image generation—0
Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models—0
Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation—0
MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and EditingCode2
Exploring Incompatible Knowledge Transfer in Few-shot Image GenerationCode1
Magnitude Invariant Parametrizations Improve Hypernetwork LearningCode1
Text-Conditional Contextualized Avatars For Zero-Shot Personalization—0
Identity Encoder for Personalized Diffusion—0
M2T: Masking Transformers Twice for Faster Decoding—0
AutoSplice: A Text-prompt Manipulated Image Dataset for Media ForensicsCode1
Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image GenerationCode1
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images—0
ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis—0
What does CLIP know about a red circle? Visual prompt engineering for VLMs—0
Expressive Text-to-Image Generation with Rich TextCode2
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and ReconstructionCode2
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image GenerationCode3
PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face InpaintingCode1
NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANsCode1
Gradient-Free Textual Inversion—0
SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRI—0
Diffusion Models for Constrained DomainsCode1
Unified Multi-Modal Image Synthesis for Missing Modality Imputation—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