Conditional Adversarial Generative Flow for Controllable Image Synthesis

04/03/2019
by   Rui Liu, et al.
0

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.

READ FULL TEXT

page 6

page 7

page 8

research
07/09/2018

Glow: Generative Flow with Invertible 1x1 Convolutions

Flow-based generative models (Dinh et al., 2014) are conceptually attrac...
research
02/16/2023

3D-aware Conditional Image Synthesis

We propose pix2pix3D, a 3D-aware conditional generative model for contro...
research
03/24/2023

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

Conditional image-to-video (cI2V) generation aims to synthesize a new pl...
research
12/15/2019

C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds

Flow-based generative models have highly desirable properties like exact...
research
12/16/2020

Latent Space Conditioning on Generative Adversarial Networks

Generative adversarial networks are the state of the art approach toward...
research
05/03/2023

Nonparametric Generative Modeling with Conditional and Locally-Connected Sliced-Wasserstein Flows

Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric g...
research
07/11/2018

Variational Capsules for Image Analysis and Synthesis

A capsule is a group of neurons whose activity vector models different p...

Please sign up or login with your details

Forgot password? Click here to reset