论文标题
EPNET：带有图像语义的增强点功能，用于3D对象检测
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
论文作者
论文摘要
在本文中，我们旨在解决3D检测任务中的两个关键问题，包括对多个传感器的开发〜（即Lidar Point Cloud和Camera Image），以及本地化和分类置信度之间的不一致性。为此，我们提出了一个新颖的融合模块，以以点上的方式以语义图像特征增强点特征，而无需任何图像注释。此外，采用一致性执行损失来明确鼓励本地化和分类信心的一致性。我们设计了一个名为EPNET的端到端可学习框架，以集成这两个组件。 Kitti和Sun-RGBD数据集的广泛实验证明了EPNET优于最新方法。代码和模型可在：\ url {https://github.com/happinesslz/epnet}中获得。
In this paper, we aim at addressing two critical issues in the 3D detection task, including the exploitation of multiple sensors~(namely LiDAR point cloud and camera image), as well as the inconsistency between the localization and classification confidence. To this end, we propose a novel fusion module to enhance the point features with semantic image features in a point-wise manner without any image annotations. Besides, a consistency enforcing loss is employed to explicitly encourage the consistency of both the localization and classification confidence. We design an end-to-end learnable framework named EPNet to integrate these two components. Extensive experiments on the KITTI and SUN-RGBD datasets demonstrate the superiority of EPNet over the state-of-the-art methods. Codes and models are available at: \url{https://github.com/happinesslz/EPNet}.
