Burst Imaging for Light-Constrained Structure-From-Motion
This addresses the challenge for robots operating in low-light environments like underground mines or at night, though it is incremental as it builds on burst photography and existing SfM techniques.
The paper tackles the problem of 3D reconstruction from images in extremely low light conditions, where noise causes existing algorithms to fail, and demonstrates improved structure-from-motion performance with better feature performance, camera pose estimates, and more frequent convergence to correct reconstructions compared to state-of-the-art methods.
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.