"Imaging in low light is difficult because the number of photons arriving at the sensor is low. Imaging dynamic scenes in low-light environments is even more difficult because as the scene moves, pixels in adjacent frames need to be aligned before they can be denoised. Conventional CMOS image sensors (CIS) are at a particular disadvantage in dynamic low-light settings because the exposure cannot be too short lest the read noise overwhelms the signal. We propose a solution using Quanta Image Sensors (QIS) and present a new image reconstruction algorithm. QIS are single-photon image sensors with photon counting capabilities. Studies over the past decade have confirmed the effectiveness of QIS for low-light imaging but reconstruction algorithms for dynamic scenes in low light remain an open problem. We fill the gap by proposing a student-teacher training protocol that transfers knowledge from a motion teacher and a denoising teacher to a student network. We show that dynamic scenes can be reconstructed from a burst of frames at a photon level of 1 photon per pixel per frame. Experimental results confirm the advantages of the proposed method compared to existing methods."
These days QIS comes in two varieties, CMOS image sensor-based QIS ("CIS-QIS") and thanks to the work at Edinburgh, ST, EPFL and most recently Canon, SPAD-QIS. Each has its merits. Both enable a new way to think about imaging for photography, security, machines, IoT, and automobiles.
ReplyDeleteThe collaboration above, I think, grew out of a first meeting between Koltun and Chan at IISW at Snowbird last summer. Let's hope we can get back to in-person conferences before long so that such unplanned collaborations can continue to spring up.