论文标题
DH3D：强大的大规模6DOF重新定位的深层分层3D描述符
DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
论文作者
论文摘要
为了在大规模点云中重新定位，我们提出了统一全球位置识别和局部6DOF姿势改进的第一种方法。为此，我们设计了一个暹罗网络，该网络直接从RAW 3D点直接学习3D本地功能检测和描述。它集成了FlexConv和挤压和激发（SE），以确保学习的本地描述符捕获多层次的几何信息和渠道关系。对于检测3D关键，我们以无监督的方式预测局部描述符的歧视性。我们通过直接通过有效的注意机制将学习的本地描述符直接汇总来生成全球描述符。这样，本地和全局3D描述符将在一个单一前传中推断出来。各种基准的实验表明，与最先进的方法相比，我们的方法可以为全球点云检索和局部点云注册取得竞争成果。为了验证3D关键点的概括性和鲁棒性，我们证明我们的方法还可以表现出色，而不会对视觉大满贯系统生成的点云的注册进行微调。代码和相关材料可在https://vision.in.tum.de/research/vslam/dh3d上找到。
For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and description directly from raw 3D points. It integrates FlexConv and Squeeze-and-Excitation (SE) to assure that the learned local descriptor captures multi-level geometric information and channel-wise relations. For detecting 3D keypoints we predict the discriminativeness of the local descriptors in an unsupervised manner. We generate the global descriptor by directly aggregating the learned local descriptors with an effective attention mechanism. In this way, local and global 3D descriptors are inferred in one single forward pass. Experiments on various benchmarks demonstrate that our method achieves competitive results for both global point cloud retrieval and local point cloud registration in comparison to state-of-the-art approaches. To validate the generalizability and robustness of our 3D keypoints, we demonstrate that our method also performs favorably without fine-tuning on the registration of point clouds that were generated by a visual SLAM system. Code and related materials are available at https://vision.in.tum.de/research/vslam/dh3d.
