This paper proposes a GNN-based method for exploiting semantics and local
geometry to guide the identification of reliable pointcloud registration
candidates. Semantic and morphological features of the environment serve as key
reference points for registration, enabling accurate lidar-based pose
estimation. Our novel lightweight static graph structure informs our
attention-based keypoint node aggregation GNN network by identifying semantic
instance-based relationships, acting as inductive bias to significantly reduce
the computational burden of pointcloud registration. By connecting candidate
nodes and exploiting cross-graph attention, we identify confidence scores for
all potential registration correspondences, estimating the displacement between
pointcloud scans. Our pipeline enables introspective analysis of the model's
performance by correlating it with the individual contributions of local
structures in the environment, providing valuable insights into the system's
behaviour. We test our method on the KITTI odometry dataset, achieving
competitive accuracy compared to benchmark methods and a higher track
smoothness while relying on significantly fewer network parameters.

本文提出了一种基于 GNN 的方法，利用语义和局部几何形状来指导可靠点云注册候选项的识别，语义和形态特征作为注册的关键参考点，实现精确的激光雷达姿态估计，我们的轻量级静态图结构通过识别语义实例关系，作为一种归纳偏见，显著减少了点云注册的计算负担，通过连接候选节点和利用跨图的关注机制，我们为所有潜在的注册对应关系计算置信度得分，估计点云扫描之间的位移，我们的流程通过将模型与环境中的局部结构的个体贡献相关联，使模型的性能进行内省分析，提供有价值的系统行为洞察。我们在 KITTI 测距数据集上测试我们的方法，相较于基准方法，实现了竞争性的准确度和更高的轨迹平滑度，同时依赖 significantly fewer network parameters。