| Full name | LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs |
| Description | We propose the spatial-wise partition convolution (SW-LK Conv), to solve the efficiency issue of plain 3D large-kernel CNNs. Our large-kernel 3D CNN network, LargeKernel3D, serves as an effective solution in 3D semantic segmentation and object detection. |
| Publication title | LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs |
| Publication authors | Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia |
| Publication venue | CVPR 2023 |
| Publication URL | https://arxiv.org/abs/2206.10555 |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | Python with CUDA |
| Hardware | Tesla V100 |
| Website | https://github.com/dvlab-research/LargeKernel3D |
| Source code or download URL | https://github.com/dvlab-research/LargeKernel3D |
| Submission creation date | 17 May, 2022 |
| Last edited | 24 Apr, 2023 |