| Full name | Feature_GeometricNet: Fast Large-Scale LiDAR Point Clouds Understanding Network |
| Description | This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and outlier filtering method is designed to facilitate subsequent high-level tasks. For effective understanding purpose, we propose a deep convolutional neural network leveraging correlated feature mining and deformable convolution based geometric-aware modelling, in which the local feature relationships and geometric patterns can be fully exploited. For the efficiency issue, we put forward an inverse density sampling operation and a feature pyramid based residual learning strategy to save the computational cost and memory consumption respectively. |
| Publication title | https://arxiv.org/abs/2012.09439 |
| Publication authors | Kangcheng Liu, Ben M. Chen |
| Publication venue | arXiv Preprint |
| Publication URL | https://arxiv.org/abs/2012.09439 |
| Input Data Types | Uses Geometry Uses 3D |
| Programming language(s) | C++ |
| Hardware | GTX 1080 |
| Website | https://github.com/KangchengLiu/Feature-Geometric-Net-FG-Net |
| Source code or download URL | https://github.com/KangchengLiu/Feature-Geometric-Net-FG-Net |
| Submission creation date | 3 May, 2021 |
| Last edited | 18 May, 2021 |
| Last uploaded | 18 May, 2021 |
