DSC: Deep Scan Context Descriptor for Large-Scale Place Recognition
This addresses loop closure detection and global relocalization for robotics, but it is incremental as it builds on prior scan context methods.
The authors tackled LiDAR-based place recognition by proposing Deep Scan Context (DSC), a global descriptor that uses raw point clouds to achieve competitive results, outperforming existing methods on the KITTI dataset.
LiDAR-based place recognition is an essential and challenging task both in loop closure detection and global relocalization. We propose Deep Scan Context (DSC), a general and discriminative global descriptor that captures the relationship among segments of a point cloud. Unlike previous methods that utilize either semantics or a sequence of adjacent point clouds for better place recognition, we only use raw point clouds to get competitive results. Concretely, we first segment the point cloud egocentrically to acquire centroids and eigenvalues of the segments. Then, we introduce a graph neural network to aggregate these features into an embedding representation. Extensive experiments conducted on the KITTI dataset show that DSC is robust to scene variants and outperforms existing methods.