DSMNet: Deep High-precision 3D Surface Modeling from Sparse Point Cloud Frames

TL;DR

DSMNet is a novel learning-based framework that significantly enhances high-precision 3D surface modeling from sparse point cloud frames, addressing limitations of existing methods and datasets.

Contribution

The paper introduces DSMNet, a joint framework with density-aware registration and geometry-aware sampling, and constructs the HPMB dataset for better evaluation of point cloud modeling.

Findings

DSMNet outperforms state-of-the-art methods in PCS and PCR.

DSMNet improves modeling precision in sparse environments.

HPMB dataset provides a new benchmark for object-level modeling evaluation.

Abstract

Existing point cloud modeling datasets primarily express the modeling precision by pose or trajectory precision rather than the point cloud modeling effect itself. Under this demand, we first independently construct a set of LiDAR system with an optical stage, and then we build a HPMB dataset based on the constructed LiDAR system, a High-Precision, Multi-Beam, real-world dataset. Second, we propose an modeling evaluation method based on HPMB for object-level modeling to overcome this limitation. In addition, the existing point cloud modeling methods tend to generate continuous skeletons of the global environment, hence lacking attention to the shape of complex objects. To tackle this challenge, we propose a novel learning-based joint framework, DSMNet, for high-precision 3D surface modeling from sparse point cloud frames. DSMNet comprises density-aware Point Cloud Registration (PCR) and geometry-aware Point Cloud Sampling (PCS) to effectively learn the implicit structure feature of sparse point clouds. Extensive experiments demonstrate that DSMNet outperforms the state-of-the-art methods in PCS and PCR on Multi-View Partial Point Cloud (MVP) database. Furthermore, the experiments on the open source KITTI and our proposed HPMB datasets show that DSMNet can be generalized as a post-processing of Simultaneous Localization And Mapping (SLAM), thereby improving modeling precision in environments with sparse point clouds.