| Full name | An Efficient and Effective Large Sparse Kernel 3D Neural Network |
| Description | Autonomous systems need to process large-scale, sparse, and irregular point clouds with limited compute resources. Consequently, it is essential to develop LiDAR perception methods that are both efficient and effective. Although naively enlarging 3D kernel size can enhance performance, it will also lead to a cubically-increasing overhead. Therefore, it is crucial to develop streamlined 3D large kernel designs that eliminate redundant weights and work effectively with larger kernels. In this paper, we propose an efficient and effective Large Sparse Kernel 3D Neural Network (LSK3DNet) that leverages dynamic pruning to amplify the 3D kernel size. Our method comprises two core components: Spatial-wise Dynamic Sparsity (SDS) and Channel-wise Weight Selection (CWS). SDS dynamically prunes and regrows volumetric weights from the beginning to learn a large sparse 3D kernel. It not only boosts performance but also significantly reduces model size and computational cost. Moreover, CWS selects th |
| Publication title | LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels |
| Publication authors | Tuo Feng, Wenguan Wang, Fan Ma, Yi Yang |
| Publication venue | CVPR 2024 |
| Publication URL | https://openaccess.thecvf.com/content/CVPR2024/papers/Feng_LSK3DNet_Towards_Effective_and_Efficient_3D_Perception_with_Large_Sparse_CVPR_2024_paper.pdf |
| Input Data Types | Uses Geometry Uses 3D |
| Programming language(s) | Python,Pytorch |
| Hardware | V100 |
| Website | https://github.com/FengZicai/LSK3DNet |
| Source code or download URL | https://github.com/FengZicai/LSK3DNet |
| Submission creation date | 9 Mar, 2025 |
| Last edited | 9 Mar, 2025 |
| Last uploaded | 9 Mar, 2025 |
