It has been widely known that 3D shape models are comprehensively parameterized using point cloud and meshes. The point\ncloud particularly is much simpler to handle compared with meshes, and it also contains the shape information of a 3D model. In\nthis paper, we would like to introduce our new method to generating the 3D point cloud from a set of crucial measurements and\nshapes of importance positions. In order to find the correspondence between shapes and measurements, we introduced a method\nof representing 3D data called slice structure. A Neural Networks-based hierarchical learning model is presented to be compatible\nwith the data representation. Primary slices are generated by matching the measurements set before the whole point cloud tuned\nby Convolutional Neural Network. We conducted the experiment on a 3D human dataset which contains 1706 examples. Our\nresults demonstrate the effectiveness of the proposed framework with the average error 7.72% and fine visualization. This study\nindicates that paying more attention to local features is worthwhile when dealing with 3D shapes.
Loading....