LBurst: Learning-Based Robotic Burst Feature Extraction for 3D Reconstruction in Low Light
This work addresses the challenge of enabling drones to operate in low-light environments like night, underground mining, and search and rescue, representing an incremental advancement in robotic vision.
The paper tackles the problem of poor image quality from drone cameras in low-light conditions by developing a learning-based architecture for burst feature extraction, which improves 3D reconstruction by detecting more true features and fewer spurious ones in low signal-to-noise ratio images, demonstrating effectiveness in millilux illumination.
Drones have revolutionized the fields of aerial imaging, mapping, and disaster recovery. However, the deployment of drones in low-light conditions is constrained by the image quality produced by their on-board cameras. In this paper, we present a learning architecture for improving 3D reconstructions in low-light conditions by finding features in a burst. Our approach enhances visual reconstruction by detecting and describing high quality true features and less spurious features in low signal-to-noise ratio images. We demonstrate that our method is capable of handling challenging scenes in millilux illumination, making it a significant step towards drones operating at night and in extremely low-light applications such as underground mining and search and rescue operations.