# Attention-based Fusion for Multi-source Human Image Generation

## TL;DR

This paper introduces an attention-based method for generating human images conditioned on a target pose using multiple source appearance images, effectively leveraging complementary information without needing separate generators for different source counts.

## Contribution

It proposes a local attention mechanism for multi-source person-image generation, enabling flexible and efficient utilization of multiple appearance images.

## Key findings

- Effective multi-source image generation demonstrated
- Attention mechanism improves relevance of source information
- Method adapts to varying number of source images

## 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.