Conditional Adversarial Generative Flow for Controllable Image Synthesis
By R. Liu, Yu Liu, Xinyu Gong, Xiaogang Wang, Hongsheng Li. 2019
48 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Danilo Jimenez Rezende
- Dacheng Tao
- Aäron van den Oord
- Ming-Hsuan Yang
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
Citations in the corpus
- Shaping Belief States with Generative Environment Models for RL (2019, background): “It is known that expressive frame generative models are hard to condition [22, 23, 24, 25].”
- SRFlow: Learning the Super-Resolution Space with Normalizing Flow (2020, unknown): “Recent works have investigated conditional flow models for point cloud generation [37,51] as well as class [25] and image [3,49] conditional generation of images.”