2018/09/18 by Isaak Lim, Alexander Dielen, Lim, Isaak +5 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Numerical Analysis Techniques #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.1809.06664
openalex publication_date 2018/09/18 · openalex created_date 2022/08/03 · openalex updated_date 2026/07/28
The question of representation of 3D geometry is of vital importance when it\ncomes to leveraging the recent advances in the field of machine learning for\ngeometry processing tasks. For common unstructured surface meshes\nstate-of-the-art methods rely on patch-based or mapping-based techniques that\nintroduce resampling operations in order to encode neighborhood information in\na structured and regular manner. We investigate whether such resampling can be\navoided, and propose a simple and direct encoding approach. It does not only\nincrease processing efficiency due to its simplicity - its direct nature also\navoids any loss in data fidelity. To evaluate the proposed method, we perform a\nnumber of experiments in the challenging domain of intrinsic, non-rigid shape\ncorrespondence estimation. In comparisons to current methods we observe that\nour approach is able to achieve highly competitive results.\n