PARE-Net：面向鲁棒点云配准的位置感知旋转等变网络
PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration
AI总结：
针对现有点云配准方法旋转鲁棒性差、参数量大的问题，提出位置感知旋转等变网络PARE-Net，搭配位置感知卷积、特征假设生成器与对比旋转损失，在轻量高速的同时实现了配准性能的SOTA提升与强旋转鲁棒性。
摘要：
学习具有旋转不变性的区分性特征是点云配准的核心基础需求。现有方法通常使用对旋转敏感的网络提取特征，同时采用旋转增强的方式粗略地学习近似不变映射，这会导致网络对旋转脆弱、参数量过大，且会限制特征的区分性。为解决这些问题，我们提出了一种新型位置感知旋转等变网络，可实现高效、轻量且鲁棒的配准。该网络能提供强模型归纳偏置，用于学习旋转等变/不变特征，从而克服上述局限。为进一步提升描述子的区分性，我们提出位置感知卷积，可更好地学习局部结构的空间信息。此外，我们还提出了基于特征的假设生成器，它利用编码了细粒度结构方向的旋转等变特征生成可靠的模型假设；每个对应点对都能生成一个假设，因此比需要多个可靠对应点对的经典估计器效率更高。相应地，我们提出了对比旋转损失，以增强旋转等变特征在数据退化情况下的鲁棒性。在室内和室外数据集上的大量实验表明，我们的方法在配准召回率上显著优于SOTA方法，同时具备轻量、速度快的优势。此外，在旋转数据集上的实验证明了其对旋转变化的鲁棒性。代码可在https://github.com/yaorz97/PARENet获取。
英文摘要：
Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an approximate invariant mapping rudely. This makes networks fragile to rotations, overweight, and hinders the distinctiveness of features. To tackle these problems, we propose a novel position-aware rotation-equivariant network, for efficient, light-weighted, and robust registration. The network can provide a strong model inductive bias to learn rotation-equivariant/invariant features, thus addressing the aforementioned limitations. To further improve the distinctiveness of descriptors, we propose a position-aware convolution, which can better learn spatial information of local structures. Moreover, we also propose a feature-based hypothesis proposer. It leverages rotation-equivariant features that encode fine-grained structure orientations to generate reliable model hypotheses. Each correspondence can generate a hypothesis, thus it is more efficient than classic estimators that require multiple reliable correspondences. Accordingly, a contrastive rotation loss is presented to enhance the robustness of rotation-equivariant features against data degradation. Extensive experiments on indoor and outdoor datasets demonstrate that our method significantly outperforms the SOTA methods in terms of registration recall while being lightweight and keeping a fast speed. Moreover, experiments on rotated datasets demonstrate its robustness against rotation variations. Code is available at https://github.com/yaorz97/PARENet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
