Skip to main content

Research Repository

Advanced Search

Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion

Atapour-Abarghouei, Amir; Breckon, Toby P.

Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion Thumbnail


Authors



Contributors

Aurélio Campilho
Editor

Fakhri Karray
Editor

Bart ter Haar Romeny
Editor

Abstract

We address the problem of hole filling in depth images, obtained from either active or stereo sensing, for the purposes of depth image completion in an exemplar-based framework. Most existing exemplar-based inpainting techniques, designed for color image completion, do not perform well on depth information with object boundaries obstructed or surrounded by missing regions. In the proposed method, using both color (RGB) and depth (D) information available from a common-place RGB-D image, we explicitly modify the patch prioritization term utilized for target patch ordering to facilitate improved propagation of complex texture and linear structures within depth completion. Furthermore, the query space in the source region is constrained to increase the efficiency of the approach compared to other exemplar-driven methods. Evaluations demonstrate the efficacy of the proposed method compared to other contemporary completion techniques.

Citation

Atapour-Abarghouei, A., & Breckon, T. P. (2018). Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion. In A. Campilho, F. Karray, & B. T. H. Romeny (Eds.), Image analysis and recognition : 15th International Conference, ICIAR 2018, Póvoa de Varzim, Portugal, June 27–29, 2018 ; proceedings (306-314). https://doi.org/10.1007/978-3-319-93000-8_35

Conference Name International Conference Image Analysis and Recognition
Conference Location Póvoa de Varzim, Portugal
Online Publication Date Jun 6, 2018
Publication Date Jun 6, 2018
Deposit Date Dec 10, 2018
Publicly Available Date Mar 29, 2024
Pages 306-314
Series Title Lecture notes in computer science
Series Number 10882
Series ISSN 0302-9743,1611-3349
Book Title Image analysis and recognition : 15th International Conference, ICIAR 2018, Póvoa de Varzim, Portugal, June 27–29, 2018 ; proceedings.
ISBN 9783319929996
DOI https://doi.org/10.1007/978-3-319-93000-8_35
Public URL https://durham-repository.worktribe.com/output/1143307
Related Public URLs http://breckon.eu/toby/publications/papers/abarghouei18patch.pdf

Files





You might also like



Downloadable Citations