Support PVRCNN++ based on existing PR 在现有 PR 上继续支持完善 PVRCNN++

[OpenMMLab-Assistant-004]

Support PVRCNN++ based on existing PR

在现有 PR 上继续支持完善 PVRCNN++

Previous PR](open-mmlab/mmdetection3d#2106)) has basically aligned PVRCNN++ on kitti for training accuracy, still need to:

1. modify the code according to the review comments
2. several cuda operators involved in PVRCNN++ have been PR'd in mmcv and need to be further updated and modified according to the review comments.

• review comments1]([Ops]Add voxel query vector pool ops mmcv#2495))
• review comments2]([Ops]Add three nn vector pool ops mmcv#2494))

3. use the relevant op submitted in MMCV, and ensure the training accuracy

之前的PR](open-mmlab/mmdetection3d#2106)) 已经基本对齐 PVRCNN++ 在 kitti 上训练精度，还需要：

1. 根据 review 意见修改 code
2. PVRCNN++ 涉及的几个 cuda 算子已经在 mmcv 中提了 PR， 需要进一步根据 review 意见更新修改。

• Review意见参考1]([Ops]Add voxel query vector pool ops mmcv#2495))
• Review意见参考2]([Ops]Add three nn vector pool ops mmcv#2494))

3. 使用 MMCV 中提交的相关 op，并确保训练精度

Task Information

Repository：MMDetection3D

Difficulty：Hard

Points：50

Estimated Time Consumption：28 days

Task Status

Claimant's Github ID：None

Claim Time：None

PR Link：None

Points to Note

To claim the task, please reply Claim the mission in the comment section. After claiming the task, please add our assistant bot called MeowMewo on WeChat at: openmmlabwx.

After completing the task, please submit a PR with the title starting with [MMSIG]. After submission, please reply with your PR link in the comments section of this Discussion. We will review your work as soon as possible.

在评论区回复 Claim the mission 领取任务，领取任务后请及时添加小助手喵喵微信: openmmlabwx

完成任务后提交相关链接（如是PR，标题请以[MMSIG]开头）回复到本Disucssion评论区，我们会第一时间审核您的贡献。