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 4001–4050 of 6689 papers

TitleStatusHype
Total Disentanglement of Font Images into Style and Character Class Features—0
Improving AI-generated music with user-guided training—0
Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis—0
Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction—0
Improving CNN Training using Disentanglement for Liver Lesion Classification in CT—0
Improving Compositional Text-to-image Generation with Large Vision-Language Models—0
Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings—0
Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations—0
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models—0
Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling—0
Improving Diffusion-Based Image Synthesis with Context Prediction—0
Improving Editability in Image Generation with Layer-wise Memory—0
Improving face generation quality and prompt following with synthetic captions—0
Toward Accurate and Realistic Outfits Visualization with Attention to Details—0
Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps—0
Improving GANs with A Dynamic Discriminator—0
Toward a Diffusion-Based Generalist for Dense Vision Tasks—0
Toward Joint Image Generation and Compression using Generative Adversarial Networks—0
Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance—0
Improving image synthesis with diffusion-negative sampling—0
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation—0
Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention—0
Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models—0
Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance—0
Attention-based Fusion for Multi-source Human Image Generation—0
Improving Text to Image Generation using Mode-seeking Function—0
Improving the Diffusability of Autoencoders—0
Towards Adversarial Denoising of Radar Micro-Doppler Signatures—0
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation—0
ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism—0
Improving Vision-and-Language Navigation by Generating Future-View Image Semantics—0
Towards Audio to Scene Image Synthesis using Generative Adversarial Network—0
Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers—0
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond—0
Inception: Jailbreak the Memory Mechanism of Text-to-Image Generation Systems—0
Attack Type Agnostic Perceptual Enhancement of Adversarial Images—0
In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation—0
Towards Automatic Image Editing: Learning to See another You—0
Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation—0
Towards Better Adversarial Synthesis of Human Images from Text—0
In-Domain GAN Inversion for Faithful Reconstruction and Editability—0
Attack to Fool and Explain Deep Networks—0
INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models—0
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps—0
Inference-time Scaling of Diffusion Models through Classical Search—0
Accelerated Image-Aware Generative Diffusion Modeling—0
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis—0
InfiniCity: Infinite-Scale City Synthesis—0
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm—0
Attack to Explain Deep Representation—0
Show:102550
← PrevPage 81 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