A Dual Sensor Computational Camera for High Quality Dark Videography

TL;DR

This paper introduces a dual-sensor camera capturing RGB and NIR videos simultaneously, combined with a novel neural network, to significantly improve high-quality dark videography under low-light conditions.

Contribution

It presents a new hardware design of a dual-sensor camera and a dual-channel neural network for reconstructing high-quality videos in extremely dark environments.

Findings

The dual-sensor camera effectively captures more photons in low light.

The DCMAN network improves noise suppression and detail preservation.

Experimental results show superior performance over existing methods.

Abstract

Videos captured under low light conditions suffer from severe noise. A variety of efforts have been devoted to image/video noise suppression and made large progress. However, in extremely dark scenarios, extensive photon starvation would hamper precise noise modeling. Instead, developing an imaging system collecting more photons is a more effective way for high-quality video capture under low illuminations. In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs. In hardware, we build a compact dual-sensor camera capturing RGB and NIR videos simultaneously. Computationally, we propose a dual-channel multi-frame attention network (DCMAN) utilizing spatial-temporal-spectral priors to reconstruct the low-light RGB and NIR videos. In addition, we build a high-quality paired RGB and NIR video dataset, based on which the approach can be applied to different sensors easily by training the DCMAN model with simulated noisy input following a physical-process-based CMOS noise model. Both experiments on synthetic and real videos validate the performance of this compact dual-sensor camera design and the corresponding reconstruction algorithm in dark videography.