Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

Abstract

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing local surface manifolds embedded in 3D Euclidean space to discriminate semantic classes or object parts as additional supervision signals. This paper is the first attempt to propose a unique multi-task geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties, which can be either generated via physical computation from point clouds themselves as self-supervision signals or provided as privileged information. Owing to explicitly encoding local shape manifolds in favor of semantic analysis, the proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbone baselines and other state-of-the-art methods, which are verified in the experiments on the popular benchmarks.

arXiv comment11 pages, 8 figures, 9 tables; accepted by the IEEE Transactions on Cybernetics

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Learning Graph Embedding with Adversarial Training Methods
• PCPNET: Learning Local Shape Properties from Raw Point Clouds
• Learning Using Privileged Information: SVM+ and Weighted SVM
• Revisiting Self-Supervised Visual Representation Learning

Cited by in corpus (4)

• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds