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 1851–1900 of 6689 papers

TitleStatusHype
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space OptimizationCode1
ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane ReflectionsCode1
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image SynthesisCode1
DMM: Building a Versatile Image Generation Model via Distillation-Based Model MergingCode1
Conditional Vector Graphics Generation for Music Cover ImagesCode1
Fully Spiking Variational AutoencoderCode1
Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image CorrectionCode1
GAN-Control: Explicitly Controllable GANsCode1
SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over TimeCode1
SRNDiff: Short-term Rainfall Nowcasting with Condition Diffusion ModelCode1
GEM: Boost Simple Network for Glass Surface Segmentation via Segment Anything Model and Data SynthesisCode1
SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven GenerationCode1
Full-Glow: Fully conditional Glow for more realistic image generationCode1
Causal Inference via Style Transfer for Out-of-distribution GeneralisationCode1
Stable Target Field for Reduced Variance Score Estimation in Diffusion ModelsCode1
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksCode1
CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationCode1
Stay Positive: Non-Negative Image Synthesis for Augmented RealityCode1
From Image to Imuge: Immunized Image GenerationCode1
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image SynthesisCode1
Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNNCode1
Frequency Domain Image Translation: More Photo-realistic, Better Identity-preservingCode1
Accelerating Diffusion Sampling with Optimized Time StepsCode1
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANsCode1
Frido: Feature Pyramid Diffusion for Complex Scene Image SynthesisCode1
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image GenerationCode1
Freestyle Layout-to-Image SynthesisCode1
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person ImagesCode1
From Face to Natural Image: Learning Real Degradation for Blind Image Super-ResolutionCode1
Learning to Generate Levels From NothingCode1
DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model StatisticsCode1
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel SynthesisCode1
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style TransferCode1
Frame Interpolation with Consecutive Brownian Bridge DiffusionCode1
FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic DataCode1
Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image GenerationCode1
DRAW: A Recurrent Neural Network For Image GenerationCode1
Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value DecompositionCode1
Style is a Distribution of FeaturesCode1
StyleNAT: Giving Each Head a New PerspectiveCode1
FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded SamplingCode1
Conditional Image Synthesis With Auxiliary Classifier GANsCode1
Conditional Image Generation with Score-Based Diffusion ModelsCode1
Generating Diverse High-Fidelity Images with VQ-VAE-2Code1
ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram DigitizationCode1
Fully Spiking Denoising Diffusion Implicit ModelsCode1
SuperStyleNet: Deep Image Synthesis with Superpixel Based Style EncoderCode1
SupResDiffGAN a new approach for the Super-Resolution taskCode1
Generator Knows What Discriminator Should Learn in Unconditional GANsCode1
FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptionsCode1
Show:102550
← PrevPage 38 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