论文标题
通过局部几何先验的辅助监督改善点云的语义分析
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
论文作者
论文摘要
现有的深度学习算法用于点云分析主要涉及以监督的学习方式从当地几何形状进行全球配置发现语义模式。但是，很少有探索几何特性揭示了嵌入3D欧几里得空间中的局部表面歧管，以区分语义类别或对象部分作为其他监督信号。本文是提出独特的多任务几何学习网络的首次尝试，通过具有局部形状属性的辅助几何学习来改善语义分析，这可以通过从点云本身作为自学意义的信号来生成，或者作为自学信息提供。由于明确编码了局部形状的歧管以支持语义分析，因此提出的几何学自学和特权学习算法可以实现与其主链基准和其他最先进的方法的卓越性能，这些方法在流行的基准标准的实验中得到了证实。
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.
