University of Oulu

Nguyen-Ha P., Huynh L., Rahtu E., Heikkilä J. (2019) Predicting Novel Views Using Generative Adversarial Query Network. In: Felsberg M., Forssén PE., Sintorn IM., Unger J. (eds) Image Analysis. SCIA 2019. Lecture Notes in Computer Science, vol 11482. Springer, Cham. https://doi.org/10.1007/978-3-030-20205-7_2

Predicting novel views using generative adversarial query network

Saved in:
Author: Nguyen-Ha, Phong1; Huynh, Lam1; Rahtu, Esa2;
Organizations: 1Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2Tampere University, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 2.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2020110989735
Language: English
Published: Springer Nature, 2019
Publish Date: 2020-11-09
Description:

Abstract

The problem of predicting a novel view of the scene using an arbitrary number of observations is a challenging problem for computers as well as for humans. This paper introduces the Generative Adversarial Query Network (GAQN), a general learning framework for novel view synthesis that combines Generative Query Network (GQN) and Generative Adversarial Networks (GANs). The conventional GQN encodes input views into a latent representation that is used to generate a new view through a recurrent variational decoder. The proposed GAQN builds on this work by adding two novel aspects: First, we extend the current GQN architecture with an adversarial loss function for improving the visual quality and convergence speed. Second, we introduce a feature-matching loss function for stabilizing the training procedure. The experiments demonstrate that GAQN is able to produce high-quality results and faster convergence compared to the conventional approach.

see all

Series: Lecture notes in computer science
ISSN: 0302-9743
ISSN-E: 1611-3349
ISSN-L: 0302-9743
ISBN: 978-3-030-20205-7
ISBN Print: 978-3-030-20204-0
Pages: 16 - 27
DOI: 10.1007/978-3-030-20205-7_2
OADOI: https://oadoi.org/10.1007/978-3-030-20205-7_2
Host publication: Image analysis : 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, proceedings
Host publication editor: Felsberg, Michael
Forssen, Per-Erik
Sintorn, Ida-Maria
Unger, Jonas
Conference: Scandinavian Conference on Image Analysis
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Subjects:
Copyright information: © Springer Nature Switzerland AG 2019. This is a post-peer-review, pre-copyedit version of an article published in Image analysis : 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, proceedings. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-20205-7_2.