Chen Yilin, Mei Yang, Lu Tao, Zou Lu, Liao Xiangyun, He Fazhi
School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, 430073, China; Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430073, China.
School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, 430073, China.
Neural Netw. 2025 Aug 7;193:107966. doi: 10.1016/j.neunet.2025.107966.
In recent years Transformers have achieved significant success in the field of 3D vision due to their inherent advantages in capturing global correlations between features. However, this can be a drawback in point cloud registration, especially in scenes with low overlap rates, where a large number of non-overlapping points can lead to ineffective or even negative attention allocation. Moreover, existing RANSAC-based registration estimators usually require a large number of iterations to obtain acceptable results, resulting in significant computational overhead. To address the above issues, we propose LDGR, which achieves robust registration in low overlap scenarios by utilizing a feature extractor with adaptive receptive fields and graphical feature awareness. Firstly, we proposed a 3D convolutional method with an adaptive receptive field named Adaptive Point Convolution (APConv) as the feature extractor. Its distinguishing feature is that the receptive field of the convolutional kernel is obtained through learning, which enables it to more flexibly handle irregular and unordered point clouds, thereby extracting richer and more diverse point features. Furthermore, to overcome the dilemma in cases of low overlap, we improved the transformer with rich local geometric information embedding and graphical feature awareness. This ensures that the model focuses more on the local spatial structure and features of the points during low overlap registration. Additionally, we propose a registration evaluator with local diffusion to global (LDGR). Compared to traditional RANSAC, it achieves comparable registration quality without requiring numerous iterative computations. Finally, we conducted several experiments on publicly available datasets such as 3DMatch and 3DLoMatch, KITTI odometry, ModelNet and ModelLoNet to validate the effectiveness of our method. We achieve optimal results in all four tests on ModelNet and ModelLoNet, significantly outperforming current state-of-the-art methods. Results on the challenging 3DMatch and 3DLoMatch datasets demonstrate the robustness of our method, with our inlier ratio substantially outperforming current state-of-the-art methods. Our experiments on the KITTI dataset demonstrate that LDGR performs no worse than RANSAC, while not requiring a large number of iterations.
近年来，由于Transformer在捕捉特征之间的全局相关性方面具有固有优势，因此在3D视觉领域取得了显著成功。然而，这在点云配准中可能是一个缺点，特别是在重叠率较低的场景中，大量非重叠点可能导致注意力分配无效甚至产生负面影响。此外，现有的基于随机抽样一致性（RANSAC）的配准估计器通常需要大量迭代才能获得可接受的结果，从而导致大量的计算开销。为了解决上述问题，我们提出了局部扩散到全局配准（LDGR）方法，该方法通过利用具有自适应感受野和图形特征感知的特征提取器，在低重叠场景中实现了鲁棒配准。首先，我们提出了一种具有自适应感受野的3D卷积方法，即自适应点卷积（APConv），作为特征提取器。其显著特点是卷积核的感受野是通过学习获得的，这使其能够更灵活地处理不规则和无序的点云，从而提取更丰富、更多样化的点特征。此外，为了克服低重叠情况下的困境，我们改进了Transformer，使其具有丰富的局部几何信息嵌入和图形特征感知。这确保了模型在低重叠配准过程中更关注点的局部空间结构和特征。此外，我们提出了一种从局部扩散到全局的配准评估器（LDGR）。与传统的RANSAC相比，它在不需要大量迭代计算的情况下实现了相当的配准质量。最后，我们在公开可用的数据集上进行了多项实验，如3DMatch和3DLoMatch、KITTI里程计、ModelNet和ModelLoNet，以验证我们方法的有效性。我们在ModelNet和ModelLoNet的所有四项测试中都取得了最佳结果，显著优于当前的最先进方法。在具有挑战性的3DMatch和3DLoMatch数据集上的结果证明了我们方法的鲁棒性，我们的内点率大大优于当前的最先进方法。我们在KITTI数据集上的实验表明，LDGR的性能不低于RANSAC，同时不需要大量迭代。
