Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
This work addresses the challenge of improving semantic segmentation or classification in 3D point cloud data, which is incremental as it builds on existing deep learning methods by adding geometric supervision.
The paper tackles the problem of semantic analysis on point clouds by introducing auxiliary supervision of local geometric priors, resulting in superior performance compared to backbone baselines and state-of-the-art methods on popular benchmarks.
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.