论文标题
通过密集到较高的深层域适应性稳健3D对象识别
Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation
论文作者
论文摘要
三维（3D）对象识别对于智能自主剂（例如自动驾驶汽车和机器人）在非结构化环境中有效运行至关重要。大多数最先进的方法都依赖于相对致密的点云，并且对于稀疏点云而言，性能会显着下降。无监督的域的适应性可以最大程度地减少使用最小未标记的稀疏点云之间致密点和稀疏点云之间的差异，从而节省了额外的稀疏数据收集，注释和再培训成本。在这项工作中，我们提出了一种基于点云的对象识别的新方法，并具有竞争性能，并在密集和稀疏点云上采用最先进的方法，同时仅接受密集的点云进行训练。
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud based object recognition with competitive performance with state-of-art methods on dense and sparse point clouds while being trained only with dense point clouds.
