| StyleSAN-XL |
- FID
- 1.68
|
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer 2023-01-30 |
코드 1 |
| StyleNAT |
- FID
- 2.05
|
StyleNAT: Giving Each Head a New Perspective 2022-11-10 |
코드 1 · 코드 2 |
| StyleNAT (Exposing) |
- FID
- 2.11
- FD
- 229.42
- Precision
- 0.79
- Recall
- 0.41
- Density
- 0.77
- Coverage
- 0.71
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| StyleGAN-XL |
- FID
- 2.19
|
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets 2022-02-01 |
코드 1 · 코드 2 |
| StyleGAN-XL (Exposing) |
- FID
- 2.26
- FD
- 240.07
- Precision
- 0.77
- Recall
- 0.43
- Density
- 0.68
- Coverage
- 0.63
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| PDM+CS |
- FID
- 2.57
|
Compensation Sampling for Improved Convergence in Diffusion Models 2023-12-11 |
코드 1 |
| HiT-L |
- FID
- 2.58
|
Improved Transformer for High-Resolution GANs 2021-06-14 |
코드 1 |
| Poly-INR |
- FID
- 2.72
|
Polynomial Implicit Neural Representations For Large Diverse Datasets 2023-03-20 |
코드 1 |
| R3GAN |
- FID
- 2.75
|
The GAN is dead; long live the GAN! A Modern GAN Baseline 2025-01-09 |
코드 1 |
| StyleSwin |
- FID
- 2.81
|
StyleSwin: Transformer-based GAN for High-resolution Image Generation 2021-12-20 |
코드 1 |
| StyleSwin (Exposing) |
- FID
- 2.89
- FD
- 303.21
- Precision
- 0.79
- Recall
- 0.28
- Density
- 0.71
- Coverage
- 0.64
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| HiT-B |
- FID
- 2.95
|
Improved Transformer for High-Resolution GANs 2021-06-14 |
코드 1 |
| HiT-S |
- FID
- 3.06
|
Improved Transformer for High-Resolution GANs 2021-06-14 |
코드 1 |
| InsGen |
- FID
- 3.31
|
Data-Efficient Instance Generation from Instance Discrimination 2021-06-08 |
코드 1 |
| Anycost GAN |
- FID
- 3.35
|
Anycost GANs for Interactive Image Synthesis and Editing 2021-03-04 |
코드 1 |
| CLR-GAN |
- FID
- 3.37
- Precision
- 0.71
- Recall
- 0.44
|
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction 2024-09-30 |
코드 1 |
| Projected-GAN (Official) |
- FID
- 3.39
- Precision
- 0.654
- Recall
- 0.464
|
Projected GANs Converge Faster 2021-11-01 |
코드 1 · 코드 2 · 코드 3 |
| InsGen (Exposing) |
- FID
- 3.46
- FD
- 436.26
- Precision
- 0.64
- Recall
- 0.13
- Coverage
- 0.51
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| LeCAM (StyleGAN2 + ADA) |
- FID
- 3.49
|
Regularizing Generative Adversarial Networks under Limited Data 2021-04-07 |
코드 1 |
| StyleGAN2 + ADA |
- FID
- 3.62
|
Training Generative Adversarial Networks with Limited Data 2020-06-11 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 |
| Projected-GAN (Exposing) |
- FID
- 4.29
- FD
- 589.20
- Precision
- 0.57
- Recall
- 0.07
- Density
- 0.31
- Coverage
- 0.30
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| CIPS |
- FID
- 4.38
|
Image Generators with Conditionally-Independent Pixel Synthesis 2020-11-27 |
코드 1 · 코드 2 |
| LFM |
- FID
- 4.55
|
Flow Matching in Latent Space 2023-07-17 |
코드 1 |
| INR-GAN-bil |
- FID
- 4.95
|
Adversarial Generation of Continuous Images 2020-11-24 |
코드 1 |
| SWAGAN-Bi |
- FID
- 5.22
|
SWAGAN: A Style-based Wavelet-driven Generative Model 2021-02-11 |
코드 1 · 코드 2 |
| StyleGAN2-ada (Exposing) |
- FID
- 5.30
- FD
- 514.78
- Precision
- 0.59
- Recall
- 0.06
- Density
- 0.36
- Coverage
- 0.39
|
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2023-06-07 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| UDM (RVE) + ST |
- FID
- 5.54
|
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation 2021-06-10 |
코드 1 |
| Unleashing Transformers |
- FID
- 6.11
|
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes 2021-11-24 |
코드 1 · 코드 2 · 코드 3 |
| GANFormer |
- FID
- 7.42
|
Generative Adversarial Transformers 2021-03-01 |
코드 1 · 코드 2 |
| U-Net GAN |
- FID
- 7.48
|
A U-Net Based Discriminator for Generative Adversarial Networks 2020-02-28 |
코드 1 · 코드 2 · 코드 3 |