| Full name | Fully-Convolutional Point Networks |
| Description | Hybrid (point-to-voxel) network for deep learning on large-scale 3D data. Fully geometric - no color used. |
| Publication title | Fully-Convolutional Point Networks for Large-Scale Point Clouds |
| Publication authors | Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari |
| Publication venue | ECCV 2018 |
| Publication URL | https://arxiv.org/abs/1808.06840 |
| Input Data Types | Uses Geometry Uses 3D |
| Programming language(s) | Python, Tensorflow, Cuda |
| Hardware | Nvidia Titan X |
| Website | http://github.com/drethage/fully-convolutional-point-network |
| Source code or download URL | https://github.com/drethage/fully-convolutional-point-network |
| Submission creation date | 18 Feb, 2019 |
| Last edited | 3 Mar, 2019 |
