In this paper, we propose SpotNet: a fast, single stage, image-centric but
LiDAR anchored approach for long range 3D object detection. We demonstrate that
our approach to LiDAR/image sensor fusion, combined with the joint learning of
2D and 3D detection tasks, can lead to accurate 3D object detection with very
sparse LiDAR support. Unlike more recent bird's-eye-view (BEV) sensor-fusion
methods which scale with range $r$ as $O(r^2)$, SpotNet scales as $O(1)$ with
range. We argue that such an architecture is ideally suited to leverage each
sensor's strength, i.e. semantic understanding from images and accurate range
finding from LiDAR data. Finally we show that anchoring detections on LiDAR
points removes the need to regress distances, and so the architecture is able
to transfer from 2MP to 8MP resolution images without re-training.

通过 SpotNet 方法，结合 LiDAR 传感器融合 2D 和 3D 检测任务，实现稀疏 LiDAR 支持下准确的远距离 3D 目标检测，并且能够在不重新训练的情况下将检测结果从 2MP 分辨率图像转移到 8MP 分辨率图像上。