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 1651–1700 of 6689 papers

TitleStatusHype
Wiener Guided DIP for Unsupervised Blind Image DeconvolutionCode1
SuperStyleNet: Deep Image Synthesis with Superpixel Based Style EncoderCode1
Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GANCode1
Ensembling Off-the-shelf Models for GAN TrainingCode1
Tackling the Generative Learning Trilemma with Denoising Diffusion GANsCode1
Score-Based Generative Modeling with Critically-Damped Langevin DiffusionCode1
A Shared Representation for Photorealistic Driving SimulatorsCode1
MoFaNeRF: Morphable Facial Neural Radiance FieldCode1
SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and EditingCode1
Adaptive Feature Interpolation for Low-Shot Image GenerationCode1
TISE: Bag of Metrics for Text-to-Image Synthesis EvaluationCode1
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space OptimizationCode1
GANSeg: Learning to Segment by Unsupervised Hierarchical Image GenerationCode1
3D-Aware Semantic-Guided Generative Model for Human SynthesisCode1
SegDiff: Image Segmentation with Diffusion Probabilistic ModelsCode1
D2C: Diffusion-Decoding Models for Few-Shot Conditional GenerationCode1
FENeRF: Face Editing in Neural Radiance FieldsCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Diffusion Autoencoders: Toward a Meaningful and Decodable RepresentationCode1
Vector Quantized Diffusion Model for Text-to-Image SynthesisCode1
LAFITE: Towards Language-Free Training for Text-to-Image GenerationCode1
Conditional Image Generation with Score-Based Diffusion ModelsCode1
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized CodesCode1
Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured SequencesCode1
NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtionCode1
Few-shot Image Generation with Mixup-based Distance LearningCode1
Lossless Compression with Probabilistic CircuitsCode1
L-Verse: Bidirectional Generation Between Image and TextCode1
Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GANCode1
Contrastive Feature Loss for Image PredictionCode1
Seamless Satellite-image SynthesisCode1
Realistic galaxy image simulation via score-based generative modelsCode1
Integrating Visuospatial, Linguistic, and Commonsense Structure into Story VisualizationCode1
Generative Occupancy Fields for 3D Surface-Aware Image SynthesisCode1
Projected GANs Converge FasterCode1
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image SynthesisCode1
Resampling Base Distributions of Normalizing FlowsCode1
Scatterbrain: Unifying Sparse and Low-rank Attention ApproximationCode1
From Image to Imuge: Immunized Image GenerationCode1
Hierarchical Transformers Are More Efficient Language ModelsCode1
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face GenerationCode1
Integrating Visuospatial, Linguistic and Commonsense Structure into Story VisualizationCode1
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs TheoryCode1
Wav2CLIP: Learning Robust Audio Representations From CLIPCode1
Controllable and Compositional Generation with Latent-Space Energy-Based ModelsCode1
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel SynthesisCode1
Unifying Multimodal Transformer for Bi-directional Image and Text GenerationCode1
StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image SynthesisCode1
Illiterate DALL-E Learns to ComposeCode1
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without RetrainingCode1
Show:102550
← PrevPage 34 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