Improving Distant 3D Object Detection Using 2D Box Supervision

arXiv:2403.09230v1 Announce Type: new
Abstract: Improving the detection of distant 3d objects is an important yet challenging task. For camera-based 3D perception, the annotation of 3d bounding relies heavily on LiDAR for accurate depth information. As such, the distance of annotation is often limited due to the sparsity of LiDAR points on distant objects, which hampers the capability of existing detectors for long-range scenarios. We address this challenge by considering only 2D box supervision for distant objects since they are …

3d object 3d object detection 3d objects abstract annotation arxiv box cs.cv detection information lidar object objects perception sparsity supervision type