Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
This addresses a critical safety issue in autonomous driving by enhancing 3D object detection for challenging scenarios, though it is an incremental improvement over existing methods.
The paper tackles the problem of detecting small, far-away, or occluded objects in LiDAR point clouds for self-driving cars by leveraging past traversals of the same scene, resulting in an average precision improvement of over 300% on challenging cases.
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely. Small, far-away, or highly occluded objects are particularly challenging because there is limited information in the LiDAR point clouds for detecting them. To address this challenge, we leverage valuable information from the past: in particular, data collected in past traversals of the same scene. We posit that these past data, which are typically discarded, provide rich contextual information for disambiguating the above-mentioned challenging cases. To this end, we propose a novel, end-to-end trainable Hindsight framework to extract this contextual information from past traversals and store it in an easy-to-query data structure, which can then be leveraged to aid future 3D object detection of the same scene. We show that this framework is compatible with most modern 3D detection architectures and can substantially improve their average precision on multiple autonomous driving datasets, most notably by more than 300% on the challenging cases.