| Full name | FuseNet-SparseFusion5 |
| Description | We train the FuseNet-SF5 on the ScanNet v2 dataset. During training, we resize the images and depth maps to 240x320 and upsample the results with the nearest-neighbor interpolation to the full resolution during test. |
| Publication title | FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture |
| Publication authors | Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers |
| Publication venue | ACCV 2016 |
| Publication URL | https://link.springer.com/chapter/10.1007/978-3-319-54181-5_14 |
| Input Data Types | Uses Color,Uses Geometry Uses 2D |
| Programming language(s) | Python with CUDA |
| Hardware | Intel® Xeon(R) CPU E5-2623 v3, GeForce TITAN X (Pascal) |
| Website | https://hazirbas.com/projects/fusenet/ |
| Source code or download URL | https://github.com/MehmetAygun/fusenet-pytorch |
| Submission creation date | 3 Dec, 2018 |
| Last edited | 3 Dec, 2018 |
