TY - GEN
T1 - Seeing in Extra Darkness Using a Deep-Red Flash
AU - Xiong, Jinhui
AU - Wang, Jian
AU - Heidrich, Wolfgang
AU - Nayar, Shree
N1 - KAUST Repository Item: Exported on 2021-11-05
PY - 2021
Y1 - 2021
N2 - We propose a new flash technique for low-light imaging, using deep-red light as an illuminating source. Our main observation is that in a dim environment, the human eye mainly uses rods for the perception of light, which are not sensitive to wavelengths longer than 620nm, yet the camera sensor still has a spectral response. We propose a novel modulation strategy when training a modern CNN model for guided image filtering, fusing a noisy RGB frame and a flash frame. This fusion network is further extended for video reconstruction. We have built a prototype with minor hardware adjustments and tested the new flash technique on a variety of static and dynamic scenes. The experimental results demonstrate that our method produces compelling reconstructions, even in extra dim conditions.
AB - We propose a new flash technique for low-light imaging, using deep-red light as an illuminating source. Our main observation is that in a dim environment, the human eye mainly uses rods for the perception of light, which are not sensitive to wavelengths longer than 620nm, yet the camera sensor still has a spectral response. We propose a novel modulation strategy when training a modern CNN model for guided image filtering, fusing a noisy RGB frame and a flash frame. This fusion network is further extended for video reconstruction. We have built a prototype with minor hardware adjustments and tested the new flash technique on a variety of static and dynamic scenes. The experimental results demonstrate that our method produces compelling reconstructions, even in extra dim conditions.
UR - http://hdl.handle.net/10754/673132
UR - https://ieeexplore.ieee.org/document/9578549/
U2 - 10.1109/CVPR46437.2021.00987
DO - 10.1109/CVPR46437.2021.00987
M3 - Conference contribution
SN - 978-1-6654-4510-8
BT - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
ER -