Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major challenge because existing hard assignment methods cannot deal with outliers naturally. Alternatively, the soft matching-based methods have been proposed to learn the matching probability rather than hard assignment. However, in this paper, we prove that these methods have an inherent ambiguity causing many deceptive correspondences. To address the above challenges, we propose to learn a partial permutation matching matrix, which does not assign corresponding points to outliers, and implements hard assignment to prevent ambiguity. However, this proposal poses two new problems, i.e., existing hard assignment algorithms can only solve a full rank permutation matrix rather than a partial permutation matrix, and this desired matrix is defined in the discrete space, which is non-differentiable. In response, we design a dedicated soft-to-hard (S2H) matching procedure within the registration pipeline consisting of two steps: solving the soft matching matrix (S-step) and projecting this soft matrix to the partial permutation matrix (H-step). Specifically, we augment the profit matrix before the hard assignment to solve an augmented permutation matrix, which is cropped to achieve the final partial permutation matrix. Moreover, to guarantee end-to-end learning, we supervise the learned partial permutation matrix but propagate the gradient to the soft matrix instead. Our S2H matching procedure can be easily integrated with existing registration frameworks, which has been verified in representative frameworks including DCP, RPMNet, and DGR. Extensive experiments have validated our method, which creates a new state-of-the-art performance for robust 3D point cloud registration. The code will be made public.
翻译:尽管在基于深学习的3D点云处理方面取得了相当大的进展,但如何获得准确的通信以进行稳健的注册仍然是一个重大挑战,因为现有的硬任务分配方法无法自然地处理外部线。 或者,基于软匹配方法的建议是为了学习匹配概率而不是硬任务。 然而,在本文中,我们证明这些方法具有内在的模糊性,导致了许多欺骗性通信。为了应对上述挑战,我们建议学习一个部分对齐匹配矩阵,该矩阵不为外部线指定相应的点,而执行硬任务分配以防止模糊性。然而,这一提议提出了两个新的问题,即现有的硬任务分配算法只能解决完整级的变异矩阵,而不是部分变异矩阵。在离散空间中,我们提出了这种期望的矩阵,这是不可区别的。作为回应,我们设计了一个专门的软对硬对硬的(S2H)匹配程序,由两个步骤组成:解决软的对齐矩阵(S-Pl),并且将这一软矩阵投放到部分变异矩阵上(H-),我们用“H-steproal ”的变式矩阵来改进了整个流动过程。具体地,我们在S-ral IM矩阵中,我们从S-ral 学习了“S-ral ral 将提升到“S-ral ral ral ral”到“xl”到“S-l”到“S-l”到“S-l”到“S-lation-x”到“S-l-lal-loration”到“S-l-l-l-x”到“我们学习”到“S-lation-xxx”到“S-xal-l-l-l-l-x-x-x-x-x-x-x-x-x-x-x-xx-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x