无需标注数据，通过自蒸馏实现点云配准的无监督学习
Unsupervised Point Cloud Registration with Self-Distillation
- 用教师-学生结构，让模型自动生成匹配标签
- 在3DMatch上优于现有方法，且可泛化到雷达数据
- 适合缺乏标注数据的自动驾驶与机器人场景
刚性点云配准是机器人和自动驾驶中的基础问题。当前深度学习方法需依赖真实位姿标注进行训练，但获取这些标注成本高昂。为此，本文提出一种无监督自蒸馏方法：将样本输入教师网络，其包含可训练特征提取器和无需学习的鲁棒求解器（如RANSAC），通过优化无监督内点率来强制对应关系一致性；同时将增强视图输入学生网络进行训练。该方法避免了初始手工特征或连续帧依赖，简化了训练流程。实验表明，本方法在RGB-D基准3DMatch上表现更优，并能有效泛化至车载雷达数据，而传统特征在此失效。代码已开源。
原文摘要 · Abstract (English)
Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them. However, this training is often not scalable due to the high cost of collecting ground truth poses. Therefore, we present a self-distillation approach to learn point cloud registration in an unsupervised fashion. Here, each sample is passed to a teacher network and an augmented view is passed to a student network. The teacher includes a trainable feature extractor and a learning-free robust solver such as RANSAC. The solver forces consistency among correspondences and optimizes for the unsupervised inlier ratio, eliminating the need for ground truth labels. Our approach simplifies the training procedure by removing the need for initial hand-crafted features or consecutive point cloud frames as seen in related methods. We show that our method not only surpasses them on the RGB-D benchmark 3DMatch but also generalizes well to automotive radar, where classical features adopted by others fail. The code is available at https://github.com/boschresearch/direg .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。