A generative model for online depth fusion

Oliver J. Woodford, George Vogiatzis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a probabilistic, online, depth map fusion framework, whose generative model for the sensor measurement process accurately incorporates both long-range visibility constraints and a spatially varying, probabilistic outlier model. In addition, we propose an inference algorithm that updates the state variables of this model in linear time each frame. Our detailed evaluation compares our approach against several others, demonstrating and explaining the improvements that this model offers, as well as highlighting a problem with all current methods: systemic bias.
Original languageEnglish
Title of host publicationComputer vision – ECCV 2012
Subtitle of host publication12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, proceedings, Part V
EditorsAndrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, Cordelia Schmid
Place of PublicationBerlin (DE)
PublisherSpringer
Pages144-157
Number of pages14
ISBN (Electronic)978-3-642-33715-4
ISBN (Print)978-3-642-33714-7
DOIs
Publication statusPublished - 2012
Event12th European Conference on Computer Vision - Florence, Italy
Duration: 7 Oct 201213 Oct 2012

Publication series

NameLecture notes in computer science
PublisherSpinger
Number7576
ISSN (Print)0302-9743

Conference

Conference12th European Conference on Computer Vision
CountryItaly
CityFlorence
Period7/10/1213/10/12

Fingerprint Dive into the research topics of 'A generative model for online depth fusion'. Together they form a unique fingerprint.

  • Cite this

    Woodford, O. J., & Vogiatzis, G. (2012). A generative model for online depth fusion. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, & C. Schmid (Eds.), Computer vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, proceedings, Part V (pp. 144-157). (Lecture notes in computer science; No. 7576). Springer. https://doi.org/10.1007/978-3-642-33715-4_11