Frontal person image generation based on arbitrary‐view human images

• Published in: Computer animation and virtual worlds Vol. 35; no. 4
• Main Authors: Zhang, Yong, Zhang, Yuqing, Chen, Lufei, Yin, Baocai, Sun, Yongliang
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.07.2024
• Subjects: Annotations; arbitrary‐view images; deep learning; Feature recognition; frontal person image generation; frontal pose estimation; Generative adversarial networks; Image processing; Virtual networks
• DOI: 10.1002/cav.2234
• ISSN: 1546-4261

Frontal person images contain the richest detailed features of humans, which can effectively assist in behavioral recognition, virtual dress fitting and other applications. While many remarkable networks are devoted to the person image generation task, most of them need accurate target poses as the network inputs. However, the target pose annotation is difficult and time‐consuming. In this work, we proposed a first frontal person image generation network based on the proposed anchor pose set and the generative adversarial network. Specifically, our method first classify a rough frontal pose to the input human image based on the proposed anchor pose set, and regress all key points of the rough frontal pose to estimate an accurate frontal pose. Then, we consider the estimated frontal pose as the target pose, and construct a two‐stream generator based on the generative adversarial network to update the person's shape and appearance feature in a crossing way and generate a realistic frontal person image. Experiments on the challenging CMU Panoptic dataset show that our method can generate realistic frontal images from arbitrary‐view human images. The process of frontal person image generation based on arbitrary‐view human images.