用自编码器潜空间优化，高效实现多视角点云精准对齐。
Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space
- 将点云配准转至自编码器潜空间，提升对大角度和退化的鲁棒性。
- 在合成与真实数据上均显著优于现有方法，支持大量视角输入。
- 适合需要高鲁棒性、大规模多视角点云配准的场景。
点云刚性配准是3D计算机视觉中的基础问题。多视角情况下，目标是找到一组6自由度位姿以对齐多个对象。基于成对配准的方法依赖后续同步算法，难以扩展到多视角。生成式方法虽克服此限制，但基于高斯混合模型并使用期望最大化算法，难以处理大变换。且多数现有方法无法应对高退化情况。本文提出POLAR（POint cloud LAtent Registration），一种多视角配准方法，可高效处理大量视角，同时对高退化和大初始角度具有强鲁棒性。通过将配准问题映射至预训练自编码器的潜空间，设计考虑退化的损失函数，并开发高效的多起点优化策略。在合成与真实数据上，POLAR显著超越现有最优方法。代码开源：github.com/pypolar/polar，或通过 pip install polaregistration 安装。
原文摘要 · Abstract (English)
Point cloud rigid registration is a fundamental problem in 3D computer vision. In the multiview case, we aim to find a set of 6D poses to align a set of objects. Methods based on pairwise registration rely on a subsequent synchronization algorithm, which makes them poorly scalable with the number of views. Generative approaches overcome this limitation, but are based on Gaussian Mixture Models and use an Expectation-Maximization algorithm. Hence, they are not well suited to handle large transformations. Moreover, most existing methods cannot handle high levels of degradations. In this paper, we introduce POLAR (POint cloud LAtent Registration), a multiview registration method able to efficiently deal with a large number of views, while being robust to a high level of degradations and large initial angles. To achieve this, we transpose the registration problem into the latent space of a pretrained autoencoder, design a loss taking degradations into account, and develop an efficient multistart optimization strategy. Our proposed method significantly outperforms state-of-the-art approaches on synthetic and real data. POLAR is available at github.com/pypolar/polar or as a standalone package which can be installed with pip install polaregistration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。