Attention-based Fusion for Multi-source Human Image Generation

Stephane Lathuiliere, Enver Sangineto, Aliaksandr Siarohin, Nicu Sebe; The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 439-448

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Lathuiliere_2020_WACV,
author = {Lathuiliere, Stephane and Sangineto, Enver and Siarohin, Aliaksandr and Sebe, Nicu},
title = {Attention-based Fusion for Multi-source Human Image Generation},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}