Pose guided person image generation

• Main Authors: MA, Liqian, JIA, Xu, SUN, Qianru, SCHIELE, Bernt, TUYTELAARS, Tinne, VAN GOOL, Luc
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Person image generation; pose estimation; generative adversarial networks; Artificial Intelligence and Robotics; Computer Sciences; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/4458; https://ink.library.smu.edu.sg/context/sis_research/article/5461/viewcontent/6644_pose_guided_person_image_generation.pdf
• Institution: Singapore Management University

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 128x64 re-identification images and 256x256 fashion photos show that our model generates high-quality person images with convincing details.