论文标题
在线语义3D场景细分的融合感知点卷积
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
论文作者
论文摘要
实时RGB-D重建的公司在线语义3D细分面临着特殊的挑战，例如如何直接在逐渐融合的3D几何数据上执行3D卷积，以及如何将信息巧妙地从框架到框架融合。我们提出了一种新型的融合感知3D点卷积，该卷积直接在重建的几何表面上运行，并有效利用了高质量3D特征学习的框架间相关性。这是通过专用的动态数据结构来实现的，该数据结构组织了在线获取的点云，其中包括全球本地树。在全球范围内，我们将在线重建的3D点编译为逐渐增长的坐标间隔树，从而实现快速点插入和邻域查询。在本地，我们使用OCTREE维护每个点的邻域信息，其构造受益于全球树的快速查询。树木的水平动态更新，并帮助3D卷积有效利用时间连贯性，以在RGB-D框架上有效地融合信息。
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from frame to frame. We propose a novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high quality 3D feature learning. This is enabled by a dedicated dynamic data structure which organizes the online acquired point cloud with global-local trees. Globally, we compile the online reconstructed 3D points into an incrementally growing coordinate interval tree, enabling fast point insertion and neighborhood query. Locally, we maintain the neighborhood information for each point using an octree whose construction benefits from the fast query of the global tree.Both levels of trees update dynamically and help the 3D convolution effectively exploits the temporal coherence for effective information fusion across RGB-D frames.
