Controllable Image Generation with Semi-supervised Deep Learning and Deformable-Mean-Template Based Geometry-Appearance Disentanglement
作者：
Highlights：
• Generative controllable neural-net model by explicitly disentangling geometry and appearance.
• Learn geometry variability using population-mean template and per-individual deformations.
• Learn appearance variability in image space designed to factor out geometric variability.
• Semi-supervised variational learning with limited manually-annotated attributes.
• Empirical analysis on two large public datasets, comparing several existing methods.
摘要
•Generative controllable neural-net model by explicitly disentangling geometry and appearance.•Learn geometry variability using population-mean template and per-individual deformations.•Learn appearance variability in image space designed to factor out geometric variability.•Semi-supervised variational learning with limited manually-annotated attributes.•Empirical analysis on two large public datasets, comparing several existing methods.
论文关键词：Deep learning,variational,semi-supervised,controllable generative image model,disentangled geometry and appearance,deformable template
论文评审过程：Received 22 June 2020, Revised 11 April 2021, Accepted 18 April 2021, Available online 28 April 2021, Version of Record 15 May 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108001
