Non-line-of-sight imaging using data-driven approaches

• Main Author: Tancik, Matthew
• Other Authors: Ramesh Raskar.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2018
• Subjects: Electrical Engineering and Computer Science.
• Online Access: http://hdl.handle.net/1721.1/119568

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. === This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. === Cataloged from student-submitted PDF version of thesis. === Includes bibliographical references (pages 63-69). === Non-line-of-sight (NLOS) imaging is desirable for its many potential applications such as detecting a vehicle occluded by a building's corner or imaging through fog. Traditional NLOS imaging techniques solve an inverse problem and are limited by computational complexity and forward model accuracy. This thesis proposes the application of data-driven techniques to NLOS imaging to leverage the convolutional neural network's ability to learn invariants to scene variations. We demonstrate the classification of an object hidden behind a scattering media along with the localization and classification of an object occluded by a corner. In addition we demonstrate the use of generative neural networks to construct images from viewpoints that extend the original camera's field of view. === by Matthew Tancik. === M. Eng.