We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images. In this way, we can exploit multiple, possibly complementary images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-image generation problem in a multi-source setting.
Attention-based Fusion for Multi-source Human Image Generation / Lathuiliere, Stephane; Sangineto, Enver; Siarohin, Aliaksandr; Sebe, Nicu. - (2020), pp. 428-437. (Intervento presentato al convegno 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 tenutosi a Snowmass Village, CO, USA nel 1st-5th March 2020) [10.1109/WACV45572.2020.9093602].
Attention-based Fusion for Multi-source Human Image Generation
Lathuiliere, Stephane;Sangineto, Enver;Siarohin, Aliaksandr;Sebe, Nicu
2020-01-01
Abstract
We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images. In this way, we can exploit multiple, possibly complementary images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-image generation problem in a multi-source setting.File | Dimensione | Formato | |
---|---|---|---|
Lathuiliere_Attention-based_Fusion_for_Multi-source_Human_Image_Generation_WACV_2020_paper.pdf
accesso aperto
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
601.93 kB
Formato
Adobe PDF
|
601.93 kB | Adobe PDF | Visualizza/Apri |
Attention-based_Fusion_for_Multi-source_Human_Image_Generation.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
616.64 kB
Formato
Adobe PDF
|
616.64 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione