多边形网格
计算机科学
点云
计算
顶点(图论)
切线
稳健性(进化)
切向量
人工智能
参考坐标系
切线空间
矢量场
标量场
标量(数学)
计算机视觉
算法
帧(网络)
数学
几何学
理论计算机科学
计算机图形学(图像)
图形
基因
电信
生物化学
数学物理
化学
作者
Simone Melzi,Riccardo Spezialetti,Federico Tombari,Michael M. Bronstein,Luigi Di Stefano,Emanuele Rodolà
标识
DOI:10.1109/cvpr.2019.00476
摘要
We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the local frame at each point; importantly, it directly inherits the properties and invariance classes of the underlying scalar function, making it remarkably robust under strong sampling artifacts, vertex noise, as well as non-rigid deformations. Existing local descriptors can directly benefit from our repeatable frames, as we showcase in a selection of 3D vision and shape analysis applications where we demonstrate state-of-the-art performance in a variety of challenging settings.
科研通智能强力驱动
Strongly Powered by AbleSci AI