Polarized 3D: High-Quality Depth Sensing with Polarization Cues

被引：151

作者：

Kadambi, Achuta ^{[1
]}

Taamazyan, Vage ^{[1
,2
]}

Shi, Boxin ^{[1
,3
]}

Raskar, Ramesh ^{[1
]}

机构：

[1] MIT, Media Lab, Cambridge, MA 02139 USA

[2] Skoltech, Skolkovo, Moscow Oblast, Russia

[3] SUTD, Singapore, Singapore

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年

关键词：

D O I：

10.1109/ICCV.2015.385

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：3370 / 3378

页数：9