Attention-based Fusion for Multi-source Human Image Generation

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.
Document type :
Journal articles
Complete list of metadatas
Contributor : Stéphane Lathuilière <>
Submitted on : Monday, November 18, 2019 - 6:37:08 PM
Last modification on : Thursday, December 19, 2019 - 1:11:59 AM

Links full text


  • HAL Id : hal-02369194, version 1
  • ARXIV : 1905.02655


Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe. Attention-based Fusion for Multi-source Human Image Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, In press. ⟨hal-02369194⟩



Record views