PoNA: Pose-guided non-local attention for human pose transfer

Li, Kun, Zhang, Jinsong, Liu, Yebin, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 and Dai, Qionghai 2020. PoNA: Pose-guided non-local attention for human pose transfer. IEEE Transactions on Image Processing 29 , pp. 9584-9599. 10.1109/TIP.2020.3029455

Preview

PDF - Accepted Post-Print Version Download (5MB) | Preview

Abstract

Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention mechanism, leading to implausible and blurry results. We propose a new human pose transfer method using a generative adversarial network (GAN) with simplified cascaded blocks. In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer. We also design pre-posed image-guided pose feature update and post-posed pose-guided image feature update to better utilize the pose and image features. Our network is simple, stable, and easy to train. Quantitative and qualitative results on Market-1501 and DeepFashion datasets show the efficacy and efficiency of our model. Compared with state-of-the-art methods, our model generates sharper and more realistic images with rich details, while having fewer parameters and faster speed. Furthermore, our generated images can help to alleviate data insufficiency for person re-identification.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers (IEEE)
ISSN:	1057-7149
Date of First Compliant Deposit:	9 October 2020
Date of Acceptance:	18 September 2020
Last Modified:	07 Nov 2023 00:04
URI:	https://orca.cardiff.ac.uk/id/eprint/135494

Actions (repository staff only)

Edit Item