Conditional Adversarial Generative Flow for Controllable Image Synthesis

Abstract

Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions. This is because the potential distribution of image conditions is hard to measure precisely from its latent variable $z$. In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow). Instead of disentangling attributes from latent space, we blaze a new trail for learning an encoder to estimate the mapping from condition space to latent space in an adversarial manner. Given a specific condition $c$, CAGlow can encode it to a sampled $z$, and then enable robust conditional image synthesis in complex situations like combining person identity with multiple attributes. The proposed CAGlow can be implemented in both supervised and unsupervised manners, thus can synthesize images with conditional information like categories, attributes, and even some unknown properties. Extensive experiments show that CAGlow ensures the independence of different conditions and outperforms regular Glow to a significant extent.

Accepted by CVPR 2019

References in corpus (16)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Generative Adversarial Text to Image Synthesis
• Conditional Image Synthesis With Auxiliary Classifier GANs
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Autoencoding beyond pixels using a learned similarity metric
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• Disentangling factors of variation in deep representations using adversarial training
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Least Squares Generative Adversarial Networks
• Discovering Hidden Factors of Variation in Deep Networks
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions

Cited by in corpus (2)

• Shaping Belief States with Generative Environment Models for RL
• InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers