Neural network identification of people hidden from view with a single-pixel, single-photon detectorPiergiorgio Caramazza, Alessandro Boccolini, Daniel Buschek, Matthias Hullin, Catherine F. Higham, Robert Henderson, Roderick Murray-Smith, Daniele Faccio
Scientific Reports (Nature Publishing Group), 8, 11945; doi: 10.1038/s41598-018-30390-0, 2018.
We demonstrate a machine learning approach that can locate and identify people from time-resolved single-pixel measurements.
arXiv:1809.08044 [cs.GR], Sept. 2018, 2018.
In this paper, we present an efficient renderer for three-bounce indirect transient light transport, and use it to reconstruct objects around corners to unprecedented accuracy.
Computational Optical Sensing and Imaging, 2017.
We demonstrate the use of machine learning to classify temporal histograms of the light-echoes backscattered from bodies hidden from view around a corner, captured by a SPAD camera.
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
We show that using multi-frequency time-of-flight measurements, five different white materials can be distinguished on a per-pixel basis.
ACM Transactions on Graphics (Proc. SIGGRAPH), 34 (4), 2015.
A new computational imaging system that captures metric radial velocity information per pixel -- think of a huge array of traffic speed guns that use light instead of radar.
Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination using Inexpensive Time-of-Flight SensorsFelix Heide, Lei Xiao, Wolfgang Heidrich and Matthias B. Hullin
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
How to look around a corner using echoes of light, using low-end devices that can't even properly measure such data.
ACM Transactions on Graphics (Proc. SIGGRAPH), 32 (4), 2013.
A computational method for capturing videos of light in flight using consumer-grade imaging hardware.