Pose-driven attention-guided image generation for person re-Identification

Person re-identification (re-ID) concerns the matching of subject images across different camera views in a multi camera surveillance system. One of the major challenges in person re-ID is pose variations across the camera network, which significantly affects the appearance of a person. Existing development data lack adequate pose variations to carry out effective training of person re-ID systems. To solve this issue, in this paper we propose an end-to-end pose-driven attention-guided generative adversarial net-work, to generate multiple poses of a person. We propose to attentively learn and transfer the subject pose through an attention mechanism. A semantic-consistency loss is proposed to preserve the seman-tic information of the person during pose transfer. To ensure fine image details are realistic after pose translation, an appearance discriminator is used while a pose discriminator is used to ensure the pose of the transferred images will exactly be the same as the target pose. We show that by incorporating the proposed approach in a person re-identification framework, realistic pose transferred images and state-of-the-art re-identification results can be achieved.(c) 2022 Published by Elsevier Ltd.

Automated summary

In this paper, an end-to-end pose-driven attention-guided generative adversarial network is proposed to generate multiple poses of a person. The attention mechanism is used to learn and transfer the subject pose, and a semantic-consistency loss is proposed to preserve the semantic information during pose transfer. Appearance and pose discriminators are utilized to ensure the realism and consistency of the transferred images. Incorporating the proposed approach in a person re-identification framework achieves realistic pose transferred images and state-of-the-art re-identification results.