# Stereoscopic Dark Flash for Low-light Photography

## TL;DR

This paper introduces a novel stereoscopic camera system using dark flash technology to capture low-light images without disturbing subjects, combining hardware innovation and deep learning for high-quality results.

## Contribution

It presents a new camera configuration and imaging procedure for dark flash stereo pairs, enabling low-noise, color-preserving images in low-light conditions.

## Key findings

- Successful hardware prototype of the dark flash stereo camera
- Effective fusion technique producing high-quality low-light images
- End-to-end trained model retains color and tone while reducing noise

## Abstract

In this work, we present a camera configuration for acquiring "stereoscopic dark flash" images: a simultaneous stereo pair in which one camera is a conventional RGB sensor, but the other camera is sensitive to near-infrared and near-ultraviolet instead of R and B. When paired with a "dark" flash (i.e., one having near-infrared and near-ultraviolet light, but no visible light) this camera allows us to capture the two images in a flash/no-flash image pair at the same time, all while not disturbing any human subjects or onlookers with a dazzling visible flash. We present a hardware prototype of this camera that approximates an idealized camera, and we present an imaging procedure that let us acquire dark flash stereo pairs that closely resemble those we would get from that idealized camera. We then present a technique for fusing these stereo pairs, first by performing registration and warping, and then by using recent advances in hyperspectral image fusion and deep learning to produce a final image. Because our camera configuration and our data acquisition process allow us to capture true low-noise long exposure RGB images alongside our dark flash stereo pairs, our learned model can be trained end-to-end to produce a fused image that retains the color and tone of a real RGB image while having the low-noise properties of a flash image.