Controllable Person Image Synthesis with Attribute-Decomposed GAN
A novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes.
generative-adversarial-networks image-synthesis computer-vision pose person-image-synthesis research article code paper

  • The core idea of the proposed model is to embed human attributes into the latent space as independent codes and thus achieve flexible and continuous control of attributes via mixing and interpolation operations in explicit style representations.
  • Specifically, a new architecture consisting of two encoding pathways with style block connections is proposed to decompose the original hard mapping into multiple more accessible subtasks.

Don't forget to tag @menyifang in your comment, otherwise they may not be notified.

Authors
Share this project
Similar projects
GANSpace: Discovering Interpretable GAN Controls
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis.
BachGAN: High-Res Image Synthesis from Salient Object Layout
We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout.
Cycle GAN in TensorFlow 2.0 with Custom Loops
Implementation of "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks" by Jun-Yan Zhu et al.
Image Processing Techniques You Can Use in ML Projects
In this article, we cover the Top 6 Image Processing Techniques for Machine Learning.
Top collections