Self-Supervised Depth Estimation from Gated Images

Princeton’s Computational Imaging Lab has released a paper about ‘Self-Supervised Depth Estimation from Gated Images’, a new method for generating highly detailed depth maps from a gated camera. These cameras hold promise as an alternative to scanning LiDAR sensors. Instead of sequentially scanning a scene and directly recording depth via the photon time-of-flight (as in pulsed LiDAR sensors) gated imagers encode depth in the relative intensity of a handful of gated slices, captured at megapixel resolution.

Image: Princeton University
Princeton University


10MP CXP-12 Camera

10MP CXP-12 Camera

Mikrotron’s 10MP EoSens 10CCX12-FM CXP-12 camera with global shutter takes full advantage of the maximum performance of the Gsprint 4510 CMOS sensor, allowing color images to be captured at up to to 478fps.