课题组研究成果Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting被计算机视觉与人工智能领域A类顶会The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023接收。该研究成果第一作者为课题组硕士研究生王海平，香港大学刘缘博士为共同一作，通讯作者为董震教授和杨必胜教授。
图1 方法概述：给定N站扫描待配准点云（a），算法输出各点云位姿矩阵以是实现场景三维重建（b）。算法贡献分为两部分：（c）通过快速构建稀疏位姿图是显著减少所需两站点云配准数量，并减少两站点云误匹配概率，提升位姿解算效率和鲁棒性；（d）设计基于历史重加权的选权迭代策略进一步增强点云位姿解算可靠性。
多站点云配准是三维信息获取、建模等方面研究的热点和难点。现有多站点云配准算法多基于两站点云配准算法恢复任意两站点云之间的相对位姿关系以构建全连接相对位姿图，并基于选权迭代策略进行位姿图解算以剔除两站误匹配并恢复点云绝对位姿。然而，全连接相对位子图构建效率和鲁棒性低，极易引入大量误匹配，进而影响位姿图结算可靠性。针对上述问题，本文提出基于稀疏图构建的多站点云配准框架SGHR，算法框架如图2。
算法贡献包括稀疏图构建及基于历史重加权的位姿图解算。首先，基于两站点云重叠度及配准成功率正相关关系，算法通过网络快速估计任意两站点云间重叠度，并筛选可靠点云对恢复相对位置关系，构建稀疏位姿图；位姿图构建理论复杂度从平方级降低为线性级。随后，在根据稀疏相对位姿图解算点云绝对位姿中，提出基于历史重加权核函数的选权迭代策略，进一步提升位姿计算可靠性。相比现有多站点云配准算法，SGHR在3DMatch数据集上取得11%的配准成功率提升，在ScanNet数据集上取得13%的配准精度提升，在ETH数据集上取得99.8%的配准成功率，同时所需两站点云配准数量减少约70%。最后通过消融实验证明了所提方法的有效性。部分定量、定性配准结果如图3、图4。文章已开源于课题组代码集主页: https://github.com/WHU-USI3DV。
图3 多类型数据集定量配准结果。
图4 多类型数据集定性配准结果。
Abstract：In this paper, we present a new method for the multiview registration of point cloud. Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses. However, constructing a densely-connected graph is time-consuming and contains lots of outlier edges, which makes the subsequent IRLS struggle to find correct poses. To address the above problems, we first propose to use a neural network to estimate the overlap between scan pairs, which enables us to construct a sparse but reliable pose graph. Then, we design a novel history reweighting function in the IRLS scheme, which has strong robustness to outlier edges on the graph. In comparison with existing multiview registration methods, our method achieves 11% higher registration recall on the 3DMatch dataset and ~13% lower registration errors on the ScanNet dataset while reducing ~70% required pairwise registrations. Comprehensive ablation studies are conducted to demonstrate the effectiveness of our designs. The source code is available at https://github.com/WHU-USI3DV/SGHR.
论文预览版链接： https://arxiv.org/abs/2304.00467
代码连接： https://github.com/WHU-USI3DV/SGHR
