We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two generation branches that model the person’s appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person’s shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.

XingGAN for Person Image Generation / Tang, Hao; Bai, Song; Zhang, Li; Torr, Philip H. S.; Sebe, Nicu. - 12370:(2020), pp. 717-734. (Intervento presentato al convegno ECCV 2020 tenutosi a online (Glasgow, UK) nel 23rd–28th August 2020) [10.1007/978-3-030-58595-2_43].

XingGAN for Person Image Generation

Tang, Hao;Sebe, Nicu
2020-01-01

Abstract

We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two generation branches that model the person’s appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person’s shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.
2020
Computer Vision: 16th European Conference Proceedings, Part 25.
Cham, CH
Springer
978-3-030-58594-5
978-3-030-58595-2
Tang, Hao; Bai, Song; Zhang, Li; Torr, Philip H. S.; Sebe, Nicu
XingGAN for Person Image Generation / Tang, Hao; Bai, Song; Zhang, Li; Torr, Philip H. S.; Sebe, Nicu. - 12370:(2020), pp. 717-734. (Intervento presentato al convegno ECCV 2020 tenutosi a online (Glasgow, UK) nel 23rd–28th August 2020) [10.1007/978-3-030-58595-2_43].
File in questo prodotto:
File Dimensione Formato  
Hao123700715.pdf

Open Access dal 01/01/2023

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.99 MB
Formato Adobe PDF
5.99 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/284565
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 81
  • ???jsp.display-item.citation.isi??? ND
social impact