Timezone: »

 
Poster
Pose Guided Person Image Generation
Liqian Ma · Xu Jia · Qianru Sun · Bernt Schiele · Tinne Tuytelaars · Luc Van Gool

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #95
in Posters Mon »
This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG$^2$ utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in an adversarial way. Extensive experimental results on both 128$\times$64 re-identification images and 256$\times$256 fashion photos show that our model generates high-quality person images with convincing details.
Keywords: Deep Autoencoders · Computer Vision · Adversarial Networks · Generative Models

Author Information

Liqian Ma (KU Leuven)
Xu Jia (KU Leuven)
Qianru Sun (National University of Singapore)
Bernt Schiele (Max Planck Institute for Informatics)
Tinne Tuytelaars (KU Leuven)
Luc Van Gool (KU Leuven)

More from the Same Authors