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 5751–5800 of 6689 papers

TitleStatusHype
Exemplar-based Generative Facial Editing—0
Deep super resolution crack network (SrcNet) for improving computer vision–based automated crack detectability in in situ bridges—0
Network-to-Network Translation with Conditional Invertible Neural NetworksCode1
Region-adaptive Texture Enhancement for Detailed Person Image SynthesisCode0
SegAttnGAN: Text to Image Generation with Segmentation Attention—0
Bayesian Conditional GAN for MRI Brain Image Synthesis—0
Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation—0
Medical Image Generation using Generative Adversarial Networks—0
Co-occurrence Based Texture SynthesisCode0
Visual Relationship Detection using Scene Graphs: A Survey—0
S2IGAN: Speech-to-Image Generation via Adversarial LearningCode1
deepSELF: An Open Source Deep Self End-to-End Learning Framework—0
Medical Image Segmentation Using a U-Net type of Architecture—0
Conditional Image Generation and Manipulation for User-Specified ContentCode1
CONFIG: Controllable Neural Face Image GenerationCode1
Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images—0
Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image SynthesisCode1
Generative Adversarial Data Programming—0
Editing in Style: Uncovering the Local Semantics of GANsCode1
A Disentangling Invertible Interpretation Network for Explaining Latent RepresentationsCode1
EM-GAN: Fast Stress Analysis for Multi-Segment Interconnect Using Generative Adversarial Networks—0
Evaluation Metrics for Conditional Image Generation—0
Disentangled Image Generation Through Structured Noise InjectionCode1
Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation—0
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive LearningCode1
Efficient Neural Architecture for Text-to-Image SynthesisCode1
DeepFake Detection by Analyzing Convolutional Traces—0
Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRICode1
Panoptic-based Image Synthesis—0
Quality Guided Sketch-to-Photo Image SynthesisCode0
Cosmetic-Aware Makeup Cleanser—0
Generative Feature Replay For Class-Incremental LearningCode1
Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision—0
Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships—0
Calibrated Vehicle Paint Signatures for Simulating Hyperspectral Imagery—0
Training with Quantization Noise for Extreme Model CompressionCode1
MXR-U-Nets for Real Time Hyperspectral ReconstructionCode1
Melanoma Detection using Adversarial Training and Deep Transfer LearningCode1
Melanoma Detection using Adversarial Training and Deep Transfer LearningCode1
ControlVAE: Controllable Variational Autoencoder—0
Decoupling Global and Local Representations via Invertible Generative FlowsCode1
Cross-domain Correspondence Learning for Exemplar-based Image TranslationCode1
Learning Spatial Relationships between Samples of Patent Image Shapes—0
SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsCode1
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis—0
Adversarial Latent AutoencodersCode2
State of the Art on Neural Rendering—0
Attentive Normalization for Conditional Image GenerationCode1
Normalizing Flows with Multi-Scale Autoregressive PriorsCode1
Training End-to-end Single Image Generators without GANs—0
Show:102550
← PrevPage 116 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