Voxel RCNN.

Voxel-RCNN是一种基于体素的三维物体检测方法。该方法的目标是在保持与基于点云的方法相当的精度的同时，提高基于体素的方法的速度。该方法的设计初衷是为了实现与point-based方法相似的精度，并尽量保持与Voxel-based方法相似的速度。为了达到这个目标，Voxel-RCNN作者对基于体素的方法进行了改进。他们在论文中对比了PV-RCNN和SECOND这两个经典网络进行了分析。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *3* [Voxel-RCNN论文和逐代码解析](https://blog.csdn.net/qq_41366026/article/details/123520480)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
- *2* [Voxel-RCNN](https://blog.csdn.net/xinxiang7/article/details/113754038)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]