no code implementations • CVPR 2023 • Manasi Muglikar, Leonard Bauersfeld, Diederik Paul Moeys, Davide Scaramuzza
Our method uses the continuous event stream caused by the rotation to reconstruct relative intensities at multiple polarizer angles.
no code implementations • 20 Oct 2021 • Manasi Muglikar, Diederik Paul Moeys, Davide Scaramuzza
The depth estimation is achieved by an event-based structured light system consisting of a laser point projector coupled with a second event-based sensor tuned to detect the reflection of the laser from the scene.
no code implementations • 2 Jul 2018 • Diederik Paul Moeys, Daniel Neil, Federico Corradi, Emmett Kerr, Philip Vance, Gautham Das, Sonya A. Coleman, Thomas M. McGinnity, Dermot Kerr, Tobi Delbruck
Conventional vision CNNs are driven by camera frames at constant sample rate, thus achieving a fixed latency and power consumption tradeoff.
no code implementations • 30 Jun 2016 • Diederik Paul Moeys, Federico Corradi, Emmett Kerr, Philip Vance, Gautham Das, Daniel Neil, Dermot Kerr, Tobi Delbruck
The CNN is trained and run on data from a Dynamic and Active Pixel Sensor (DAVIS) mounted on a Summit XL robot (the predator), which follows another one (the prey).