CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

Mingye Xu

doi:10.1109/TMM.2024.3382512

2024-01-01

DOI：10.1109/TMM.2024.3382512

原文链接

原文求助

摘要

En 中文

Self-supervised learning has not been extensively investigated in the context of point cloud analysis. Current frameworks are predominantly rely on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric structures and contours but struggle to comprehend high-level semantic content. Consequently, they achieve unsatisfactory performance in downstream tasks such as classification, segmentation, etc. To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guides self-supervised reconstruction to learn semantic content in the point cloud, and thus promote discriminative power of point cloud representation. Initially, we introduce a concise contour-perturbed augmentation module for point cloud reconstruction. With guidance of geometry disentangling, we divide point cloud into contour and content components. Subsequently, we perturb the contour components and preserve the content components on the point cloud. As a result, self supervisor can effectively focus on semantic content, by reconstructing the original point cloud from such perturbed one. Next, we use this perturbed reconstruction as an assistant branch, to guide the learning of basic reconstruction branch via a distinct dual-branch consistency loss. In this case, our CP-Net not only captures structural contour but also learn semantic content for discriminative downstream tasks. Finally, we perform extensive experiments on a number of point cloud benchmarks. Part segmentation results demonstrate that our CP-Net (81.5% of mean Intersection over union) outperforms the previous self-supervised models, and narrows the gap with the fully-supervised methods. For classification, we get a competitive result with the fully-supervised methods on ModelNet40 (92.5% accuracy) and ScanObjectNN (87.9% accuracy).

Keyword:

Point cloud compression

Semantics

Feature extraction

Three-dimensional displays

Task analysis

Vectors

Geometry

3D point cloud analysis

classification

part segmentation

unsupervised learning