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 5651–5700 of 6689 papers

TitleStatusHype
Example-Guided Image Synthesis using Masked Spatial-Channel Attention and Self-Supervision—0
ForkGAN: Seeing into the Rainy NightCode1
Contrastive Learning for Unpaired Image-to-Image TranslationCode2
Cross-Domain Cascaded Deep Translation—0
CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis—0
Feature Representation Matters: End-to-End Learning for Reference-based Image Super-resolution—0
Reconstructing the Noise Variance Manifold for Image Denoising—0
Photorealism in Driving Simulations: Blending Generative Adversarial Image Synthesis with Rendering—0
Contrastive Learning for Unpaired Image-to-Image TranslationCode1
Translate the Facial Regions You Like Using Region-Wise Normalization—0
COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network—0
Generative networks as inverse problems with fractional wavelet scattering networks—0
XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms—0
Style is a Distribution of FeaturesCode1
TSIT: A Simple and Versatile Framework for Image-to-Image TranslationCode1
Multi-Metric Evaluation of Thermal-to-Visual Face Recognition—0
A novel deep learning-based method for monochromatic image synthesis from spectral CT using photon-counting detectors—0
Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism—0
Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation—0
Generative Hierarchical Features from Synthesizing ImagesCode1
Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture SearchCode1
XingGAN for Person Image GenerationCode1
Generating Person Images with Appearance-aware Pose StylizerCode1
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training DataCode1
RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval—0
Controllable Image Synthesis via SegVAE—0
Modeling Artistic Workflows for Image Generation and EditingCode1
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature EqualizationsCode1
Lessons Learned from the Training of GANs on Artificial DatasetsCode1
Closed-Form Factorization of Latent Semantics in GANsCode2
WormPose: Image synthesis and convolutional networks for pose estimation in C. elegansCode1
Impression Space from Deep Template Network—0
InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive LearningCode1
NVAE: A Deep Hierarchical Variational AutoencoderCode1
Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization—0
SofGAN: A Portrait Image Generator with Dynamic StylingCode1
Automatic Ischemic Stroke Lesion Segmentation from Computed Tomography Perfusion Images by Image Synthesis and Attention-Based Deep Neural Networks—0
Gradient Origin NetworksCode1
Meta-Learning Divergences of Variational Inference—0
Partially Conditioned Generative Adversarial Networks—0
HoughNet: Integrating near and long-range evidence for bottom-up object detectionCode1
GRAF: Generative Radiance Fields for 3D-Aware Image SynthesisCode1
BézierSketch: A generative model for scalable vector sketchesCode1
Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On—0
PerceptionGAN: Real-world Image Construction from Provided Text through Perceptual Understanding—0
Image Shape Manipulation from a Single Augmented Training SampleCode1
Sliced Iterative Normalizing FlowsCode1
Deep Geometric Texture SynthesisCode1
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition—0
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved GeneralizationCode0
Show:102550
← PrevPage 114 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