| Efficient-VDVAE: Less is more | ✓ Link | 0.51 | | 1.35 | Efficient-VDVAE | 2022-03-25 |
| Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling | | 0.61 | | | SPN Menick and Kalchbrenner (2019) | 2018-12-04 |
| MaCow: Masked Convolutional Generative Flow | ✓ Link | 0.67 | | | MaCow (Var) | 2019-02-12 |
| Score-based Generative Modeling in Latent Space | ✓ Link | 0.70 | 7.22 | | LSGM | 2021-06-10 |
| NVAE: A Deep Hierarchical Variational Autoencoder | ✓ Link | 0.70 | | | NVAE w/ flow | 2020-07-08 |
| Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models | ✓ Link | 0.72 | | | ANF Huang et al. (2020) | 2020-02-17 |
| Locally Masked Convolution for Autoregressive Models | ✓ Link | 0.74 | | | Locally Masked PixelCNN | 2020-06-22 |
| MaCow: Masked Convolutional Generative Flow | ✓ Link | 0.95 | | | MaCow (Unf) | 2019-02-12 |
| Residual Flows for Invertible Generative Modeling | ✓ Link | 0.992 | | | Residual Flow | 2019-06-06 |
| Glow: Generative Flow with Invertible 1x1 Convolutions | ✓ Link | 1.03 | | | Glow (Kingma and Dhariwal, 2018) | 2018-07-09 |
| StyleSwin: Transformer-based GAN for High-resolution Image Generation | ✓ Link | | 3.25 | | StyleSwin | 2021-12-20 |
| Improved Transformer for High-Resolution GANs | ✓ Link | | 3.39 | | HiT-B | 2021-06-14 |
| Taming Transformers for High-Resolution Image Synthesis | ✓ Link | | 10.2 | | VQGAN | 2020-12-17 |
| Adversarial Latent Autoencoders | ✓ Link | | 19.21 | | StyleALAE | 2020-04-09 |
| A Contrastive Learning Approach for Training Variational Autoencoder Priors | | | 24.79 | | NCP-VAE | 2020-10-06 |
| Latent Space Factorisation and Manipulation via Matrix Subspace Projection | ✓ Link | | 35.0 | | MSP | 2019-07-26 |
| Generative Latent Flow | ✓ Link | | 41.8 | | GLF+perceptual loss (ours) | 2019-05-24 |