This paper presents a novel framework to learn a concise geometric primitive
representation for 3D point clouds. Different from representing each type of
primitive individually, we focus on the challenging problem of how to achieve a
concise and uniform representation robustly. We employ quadrics to represent
diverse primitives with only 10 parameters and propose the first end-to-end
learning-based framework, namely QuadricsNet, to parse quadrics in point
clouds. The relationships between quadrics mathematical formulation and
geometric attributes, including the type, scale and pose, are insightfully
integrated for effective supervision of QuaidricsNet. Besides, a novel
pattern-comprehensive dataset with quadrics segments and objects is collected
for training and evaluation. Experiments demonstrate the effectiveness of our
concise representation and the robustness of QuadricsNet. Our code is available
at https://github.com/MichaelWu99-lab/QuadricsNet

该论文提出了一种新颖的框架，用于学习 3D 点云的简洁几何基元表示。与分别表示每种基元不同，我们关注如何稳健地实现简洁且统一的表示问题。我们使用二次曲面来表示包含仅有 10 个参数的多种基元，并提出了首个端到端学习的框架 QuadricsNet 来解析点云中的二次曲面。二次曲面的数学表达与几何属性（包括类型、尺度和姿态）之间的关系被巧妙地集成，以对 QuaidricsNet 进行有效监督。此外，还收集了一个新颖的模式综合的数据集，其中包含二次曲面的分段和对象，用于训练和评估。实验证明了我们简洁表示的有效性和 QuadricsNet 的鲁棒性。我们的代码可在 https://github.com/MichaelWu99-lab/QuadricsNet 获得。