podgorskiy/ALAE
PyTorch implementation of Adversarial Latent Autoencoders (ALAE), a CVPR2020 paper on GAN-based face generation.
Not currently ranked — collecting fresh signals.
star history
This repository implements the Adversarial Latent Autoencoder (ALAE) architecture from the CVPR 2020 paper. It combines autoencoder and GAN approaches to achieve both generative and representational capabilities. The method learns disentangled representations while maintaining the generative power of GANs. The implementation includes style mixing and reconstruction capabilities demonstrated on face datasets like FFHQ and CelebA-HQ.
Frequently asked
- What is podgorskiy/ALAE?
- PyTorch implementation of Adversarial Latent Autoencoders (ALAE), a CVPR2020 paper on GAN-based face generation.
- Is ALAE open source?
- Yes — podgorskiy/ALAE is an open-source project tracked on heatdrop.
- What language is ALAE written in?
- podgorskiy/ALAE is primarily written in Python.
- How popular is ALAE?
- podgorskiy/ALAE has 3.5k stars on GitHub.
- Where can I find ALAE?
- podgorskiy/ALAE is on GitHub at https://github.com/podgorskiy/ALAE.