RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds

doi:10.1007/s11263-022-01682-w

2022-09-27

PRE

DOI：10.1007/s11263-022-01682-w

原文链接

原文求助

摘要

En 中文

Deep learning has proven an effective tool for 3D point cloud processing. Currently, most deep set architectures are developed for sparse inputs (typically with a few thousand points), which are unable to provide sufficient structural statistics and semantic cues due to low resolutions. Since these architectures suffer from unacceptable computational and memory costs when consuming dense inputs, there is a pressing need in real-world applications to handle large-scale 3D point clouds. To bridge this gap, this paper presents a novel unsupervised neural architecture called RegGeoNet to parameterize an unstructured point set into a completely regular image structure dubbed as deep geometry image (DeepGI), such that spatial coordinates of unordered points are recorded in three-channel grid pixels. Intuitively, our goal is to embed irregular 3D surface points onto uniform 2D lattice grids, while trying to preserve local neighborhood consistency. Functionally, DeepGI serves as a generic representation modality for raw point cloud data and can be conveniently integrated into mature image processing pipelines. Driven by its unique structural characteristics, we are motivated to customize a set of efficient feature extractors that directly operate on DeepGls for achieving a rich variety of downstream tasks. To demonstrate the potential and universality of our proposed learning paradigms built upon DeepGls for large-scale point cloud processing, we conduct extensive experiments on various downstream tasks, including shape classification, object part segmentation, scene semantic segmentation, normal estimation, and geometry compression, where our frameworks achieve highly competitive performance, compared with state-of-the-art methods. The source code will be publicly available at htips://github.com/keeganhk/RegGeoNet.

Keyword:

Deep learning

Large-scale 3D point clouds

Regular representation

Geometry image

Unsupervised learning