<div class="csl-bib-body">
<div class="csl-entry">Cardoso, J. A., Goncalves, N., & Wimmer, M. (2020). Cost volume refinement for depth prediction. In <i>2020 25th International Conference on Pattern Recognition</i> (pp. 354–361). https://doi.org/10.34726/2164</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/19341
-
dc.identifier.uri
https://doi.org/10.34726/2164
-
dc.description.abstract
Light-field cameras are becoming more popular in the consumer market. Their data redundancy allows, in theory, to accurately refocus images after acquisition and to predict the depth of each point visible from the camera. Combined, these two features allow for the generation of full-focus images, which is impossible in traditional cameras. Multiple methods for depth prediction from light fields (or stereo) have been proposed over the years. A large subset of these methods relies on cost-volume estimates - 3D objects where each layer represents a heuristic of whether each point in the image is at a certain distance from the camera. Generally, this volume is used to regress a depth map, which is then refined for better results. In this paper, we argue that refining the cost volumes is superior to refining the depth maps in order to further increase the accuracy of depth predictions. We propose a set of cost-volume refinement algorithms and show their effectiveness.
en
dc.language.iso
en
-
dc.rights.uri
http://rightsstatements.org/vocab/InC/1.0/
-
dc.subject
Cost-Volumes
en
dc.subject
Depth Reconstruction
en
dc.subject
Light-Fields
en
dc.subject
optimization
en
dc.subject
stereo
en
dc.title
Cost volume refinement for depth prediction
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.rights.license
Urheberrechtsschutz
de
dc.rights.license
In Copyright
en
dc.identifier.doi
10.34726/2164
-
dc.contributor.affiliation
Institute of Systems and Robotics, University of Coimbra, Portuguese Mint and Official Printing Office, Lisbon