Abstract: Fourier descriptors are classical global shape descriptors with high matching speed but low accuracy. To obtain higher accuracy, a novel framework for forming Fourier descriptors is proposed ...
This repository contains an official implementation for SAGNet: Structure-aware Generative Network for 3D-Shape Modeling. This model takes voxel maps as geometry and bounding boxes as structure and ...
Abstract: Three-dimensional (3D) objects are always better than two-dimensional (2D) images for visualization. Very delicate information can be detected in 3D objects compared to 2D objects. The human ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback