- published
- 2015-03-11
- reference
- Laura Fernández Julià, and Pascal Monasse, Bilaterally Weighted Patches for Disparity Map Computation, Image Processing On Line, 5 (2015), pp. 73–89. https://doi.org/10.5201/ipol.2015.123
Communicated by Gabriele Facciolo
Demo edited by Pascal Monasse
Abstract
Visual correspondence is the key for 3D reconstruction in binocular stereovision. Local methods perform block-matching to compute the disparity, or apparent motion, of pixels between images. The simplest approach computes the distance of patches, usually square windows, and assumes that all pixels in the patch have the same disparity. A prominent artifact of the method is the "foreground fattening effet" near depth discontinuities. In order to find a more appropriate support, Yoon and Kweon introduced the use of weights based on color similarity and spatial distance, analogous to those used in the bilateral filter. This paper presents the theory of this method and the implementation we have developed. Moreover, some variants are discussed and improvements are used in the final implementation. Several examples and tests are presented and the parameters and performance of the method are analyzed.
Download
- full text manuscript: PDF low-res. (719K) PDF (4.2M) [?]
- source code: TAR/GZ
Non-Reviewed Supplementary Materials
These files and information are provided by the authors and have not been reviewed.
- Source code for rectification: TAR/GZ
History
- Note from the editor: The source code was updated on April 28, 2024 to prevent compilation errors with recent versions of GCC. The previous version of the source code can be found here.
- Note from the editor: The source code was updated on June 21, 2017 to fix a bug causing an out of bounds memory read under certain circumstances. The original source code can be found here.
- Note from the editor: the manuscript of the article was modified on 2022-01-01 to include information about its editors. The original version of the manuscript is available here.