多視角點雲配準：基於自編碼器潛在空間的優化方法

Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space

April 30, 2025

作者: Luc Vedrenne, Sylvain Faisan, Denis Fortun

cs.AI

摘要

點雲剛性配準是三維計算機視覺中的一個基礎問題。在多視角情況下，我們的目標是找到一組六維姿態來對齊一組物體。基於成對配準的方法依賴於後續的同步算法，這使得它們在視角數量增加時的可擴展性較差。生成式方法克服了這一限制，但它們基於高斯混合模型並使用期望最大化算法，因此不太適合處理大規模變換。此外，大多數現有方法無法應對高度退化情況。本文中，我們提出了POLAR（POint cloud LAtent Registration），這是一種多視角配準方法，能夠高效處理大量視角，同時對高度退化和大初始角度具有魯棒性。為實現這一點，我們將配準問題轉移到預訓練自編碼器的潛在空間中，設計了一種考慮退化的損失函數，並開發了一種高效的多起點優化策略。我們提出的方法在合成數據和真實數據上顯著優於現有最先進的方法。POLAR可在github.com/pypolar/polar獲取，或作為獨立包通過pip install polaregistration安裝。

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.