Burst Imaging for Light-Constrained Structure-From-Motion

TL;DR

This paper introduces a burst photography-based image processing technique that enhances 3D reconstruction accuracy in low light conditions, enabling robots to operate effectively in dark environments.

Contribution

It presents a novel direct image registration method within burst sequences to improve structure-from-motion in extremely low light scenarios.

Findings

Enhanced feature detection and camera pose estimation in low light.

Higher success rate of accurate 3D reconstructions compared to existing methods.

More frequent convergence to correct reconstructions in challenging scenes.

Abstract

Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this paper we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation.