[论文解读] Surface Reconstruction from Point Clouds: A Survey and a Benchmark

Zhangjin Huang, Yuxin Wen+3 more|arXiv (Cornell University)|May 5, 2022

3D Shape Modeling and Analysis被引用 23

一句话总结

点云表面重建的综述与大规模基准测试，比较经典方法与深度学习方法，并提供关于鲁棒性与泛化能力的见解。

ABSTRACT

Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete point cloud observation is a long-standing problem. The problem is technically ill-posed, and becomes more difficult considering that various sensing imperfections would appear in the point clouds obtained by practical depth scanning. In literature, a rich set of methods has been proposed, and reviews of existing methods are also provided. However, existing reviews are short of thorough investigations on a common benchmark. The present paper aims to review and benchmark existing methods in the new era of deep learning surface reconstruction. To this end, we contribute a large-scale benchmarking dataset consisting of both synthetic and real-scanned data; the benchmark includes object- and scene-level surfaces and takes into account various sensing imperfections that are commonly encountered in practical depth scanning. We conduct thorough empirical studies by comparing existing methods on the constructed benchmark, and pay special attention on robustness of existing methods against various scanning imperfections; we also study how different methods generalize in terms of reconstructing complex surface shapes. Our studies help identify the best conditions under which different methods work, and suggest some empirical findings. For example, while deep learning methods are increasingly popular, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods. We expect that the benchmark and our studies would be valuable both for practitioners and as a guidance for new innovations in future research.

研究动机与目标

• 按所使用的几何先验对现有表面重建方法进行分类（三角网化/三角剖分、光滑性、模板、建模、基于学习的方法及混合方法）。
• 引入一个大规模基准数据集（合成数据与真实扫描数据），覆盖对象级和场景级表面，并包含实际感知中的不完美之处。
• 在基准上系统评估现有方法，以揭示鲁棒性和泛化能力的优势与不足。
• 突出当前方法仍未解决的实际挑战（配准不良、数据缺失、离群点）。
• 基于实证结果，为实践者和未来的研究方向提供指南。

提出的方法

• 根据用于正则化重建的几何先验来组织与评审方法。
• 提供包含合成数据与真实扫描数据、覆盖对象级与场景级表面的大规模基准数据集，并包含真实感知的不完美。
• 进行方法的经验比较，聚焦于对数据不完美的鲁棒性和对复杂曲面的泛化能力。
• 讨论建模与学习先验，包括深度学习方法及其与经典方法的对比。
• 公开获取基准数据集和可复现实验的代码。

实验结果

研究问题

• RQ1 在实际感知不完善的情况下，现有表面重建方法表现出怎样的鲁棒性与泛化能力？
• RQ2 在鲁棒性和对复杂几何体的泛化能力方面，经典方法与深度学习方法的比较如何？
• RQ3 哪些先验与表示（例如三角剖分、光滑性、模板、隐式/显式模型）在噪声、离群值和配准不良下最影响重建质量？
• RQ4 在多视角配准不良、数据缺失和离群点方面，当前方法存在哪些尚未解决的挑战？
• RQ5 基准测试应如何设计，以更好地反映实际扫描条件和评估指标？

主要发现

• 在基准测试中，一些经典方法显示出比近代深度学习方法更强的鲁棒性和泛化能力。
• 表面法线在提升重建质量方面发挥关键作用，即使法线信息并不完美。
• 评估指标与视觉质量之间存在不一致，表明需要更基础的基准评测。
• 配准不良、数据缺失和离群点在整个基准中仍对所有方法构成挑战。
• 深度学习方法显示出潜力，但在对高度复杂形状的泛化方面仍有挑战。
• 该基准在现实感知不完善条件下联合评估对象级与场景级表面。