Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism

TL;DR

This paper introduces a self-supervised method for completing incomplete 3D vehicle scans in real traffic scenes, leveraging consecutive frames and scene context without requiring complete training data.

Contribution

It proposes a novel self-supervised approach that uses scene-aware bottom-up mechanisms and vehicle memory banks to improve real-world point cloud completion.

Findings

Achieves effective point cloud completion on KITTI and nuScenes datasets.

Enhances downstream 3D detection performance.

Operates without any complete shape data during training.

Abstract

Real scans always miss partial geometries of objects due to the self-occlusions, external-occlusions, and limited sensor resolutions. Point cloud completion aims to refer the complete shapes for incomplete 3D scans of objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process, which are usually obtained from synthetic datasets. It is not applicable for real-world scans due to the domain gap. In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data. Based on the symmetry and similarity of vehicles, we make use of consecutive point cloud frames to construct vehicle memory bank as reference. We design a bottom-up mechanism to focus on both local geometry details and global shape features of inputs. In addition, we design a scene-graph in the network to pay attention to the missing parts by the aid of neighboring vehicles. Experiments show that TraPCC achieve good performance for real-scan completion on KITTI and nuScenes traffic datasets even without any complete data in training. We also show a downstream application of 3D detection, which benefits from our completion approach.