Polarized 3D: High-Quality Depth Sensing with Polarization Cues
Name
manuscript_iccv.pdf
Size
64.34 MB
Format
Adobe PDF
Checksum (MD5)
382a0e1b83e96f5f933f0ff5765ed615
Author(s)
Kadambi, Achuta
Taamazyan, Vage
Shi, Boxin
Raskar, Ramesh
Date Issued
2015
Journal
Proceedings of the 2015 International Conference on Computer Vision
Publisher
Computer Vision Foundation
Citation
Kadambi, Achuta, Vage Taamazyan, Boxin Shi, and Ramesh Raskar. "Polarized 3D: High-Quality Depth Sensing with Polarization Cues." 2015 International Conference on Computer Vision (2015).
Version
Author's final manuscript
Abstract
Coarse depth maps can be enhanced by using the shape information from polarization cues. We propose a framework to combine surface normals from polarization (hereafter polarization normals) with an aligned depth map. Polarization normals have not been used for depth enhancement before. This is because polarization normals suffer from physics-based artifacts, such as azimuthal ambiguity, refractive distortion and fronto-parallel signal degradation. We propose a framework to overcome these key challenges, allowing the benefits of polarization to be used to enhance depth maps. Our results demonstrate improvement with respect to state-of-the-art 3D reconstruction techniques.
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Kadambi_Polarized_3D_High-Quality_ICCV_2015_paper.pdf
