SCP: Scene Completion Pre-training for 3D Object Detection
This addresses the data annotation bottleneck for researchers and practitioners in autonomous driving and robotics, though it is incremental as it builds on existing detectors.
The paper tackles the problem of 3D object detection requiring large annotated datasets by proposing Scene Completion Pre-training (SCP), which reduces the need for labeled data, allowing state-of-the-art detectors to achieve comparable performance with only 20% labeled data.
3D object detection using LiDAR point clouds is a fundamental task in the fields of computer vision, robotics, and autonomous driving. However, existing 3D detectors heavily rely on annotated datasets, which are both time-consuming and prone to errors during the process of labeling 3D bounding boxes. In this paper, we propose a Scene Completion Pre-training (SCP) method to enhance the performance of 3D object detectors with less labeled data. SCP offers three key advantages: (1) Improved initialization of the point cloud model. By completing the scene point clouds, SCP effectively captures the spatial and semantic relationships among objects within urban environments. (2) Elimination of the need for additional datasets. SCP serves as a valuable auxiliary network that does not impose any additional efforts or data requirements on the 3D detectors. (3) Reduction of the amount of labeled data for detection. With the help of SCP, the existing state-of-the-art 3D detectors can achieve comparable performance while only relying on 20% labeled data.