Skip to content

Commit

Permalink
Merge f9a3a5e into be2029d
Browse files Browse the repository at this point in the history
  • Loading branch information
xizaoqu authored Mar 23, 2023
2 parents be2029d + f9a3a5e commit 8475203
Show file tree
Hide file tree
Showing 6 changed files with 128 additions and 51 deletions.
56 changes: 31 additions & 25 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
<li><a href="configs/dgcnn">DGCNN (TOG'2019)</a></li>
<li>DLA (CVPR'2018)</li>
<li>MinkResNet (CVPR'2019)</li>
<li><a href="configs/cylinder3d">Cylinder3D (CVPR'2021)</a></li>
</ul>
</td>
<td>
Expand Down Expand Up @@ -212,6 +213,10 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
</ul>
</td>
<td>
<li><b>Outdoor</b></li>
<ul>
<li><a href="configs/cylinder3d">Cylinder3D (CVPR'2021)</a></li>
</ul>
<li><b>Indoor</b></li>
<ul>
<li><a href="configs/pointnet2">PointNet++ (NeurIPS'2017)</a></li>
Expand All @@ -226,31 +231,32 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
</tbody>
</table>

| | ResNet | PointNet++ | SECOND | DGCNN | RegNetX | DLA | MinkResNet |
| :-----------: | :----: | :--------: | :----: | :---: | :-----: | :-: | :--------: |
| SECOND ||||||||
| PointPillars ||||||||
| FreeAnchor ||||||||
| VoteNet ||||||||
| H3DNet ||||||||
| 3DSSD ||||||||
| Part-A2 ||||||||
| MVXNet ||||||||
| CenterPoint ||||||||
| SSN ||||||||
| ImVoteNet ||||||||
| FCOS3D ||||||||
| PointNet++ ||||||||
| Group-Free-3D ||||||||
| ImVoxelNet ||||||||
| PAConv ||||||||
| DGCNN ||||||||
| SMOKE ||||||||
| PGD ||||||||
| MonoFlex ||||||||
| SA-SSD ||||||||
| FCAF3D ||||||||
| PV-RCNN ||||||||
| | ResNet | PointNet++ | SECOND | DGCNN | RegNetX | DLA | MinkResNet | Cylinder3D |
| :-----------: | :----: | :--------: | :----: | :---: | :-----: | :-: | :--------: | :--------: |
| SECOND |||||||||
| PointPillars |||||||||
| FreeAnchor |||||||||
| VoteNet |||||||||
| H3DNet |||||||||
| 3DSSD |||||||||
| Part-A2 |||||||||
| MVXNet |||||||||
| CenterPoint |||||||||
| SSN |||||||||
| ImVoteNet |||||||||
| FCOS3D |||||||||
| PointNet++ |||||||||
| Group-Free-3D |||||||||
| ImVoxelNet |||||||||
| PAConv |||||||||
| DGCNN |||||||||
| SMOKE |||||||||
| PGD |||||||||
| MonoFlex |||||||||
| SA-SSD |||||||||
| FCAF3D |||||||||
| PV-RCNN |||||||||
| Cylinder3D |||||||||

**Note:** All the about **300+ models, methods of 40+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/model_zoo.md) can be trained or used in this codebase.

Expand Down
56 changes: 31 additions & 25 deletions README_zh-CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱,下一代
<li><a href="configs/dgcnn">DGCNN (TOG'2019)</a></li>
<li>DLA (CVPR'2018)</li>
<li>MinkResNet (CVPR'2019)</li>
<li><a href="configs/cylinder3d">Cylinder3D (CVPR'2021)</a></li>
</ul>
</td>
<td>
Expand Down Expand Up @@ -193,6 +194,10 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱,下一代
</ul>
</td>
<td>
<li><b>室外</b></li>
<ul>
<li><a href="configs/cylinder3d">Cylinder3D (CVPR'2021)</a></li>
</ul>
<li><b>室内</b></li>
<ul>
<li><a href="configs/pointnet2">PointNet++ (NeurIPS'2017)</a></li>
Expand All @@ -207,31 +212,32 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱,下一代
</tbody>
</table>

| | ResNet | PointNet++ | SECOND | DGCNN | RegNetX | DLA | MinkResNet |
| :-----------: | :----: | :--------: | :----: | :---: | :-----: | :-: | :--------: |
| SECOND ||||||||
| PointPillars ||||||||
| FreeAnchor ||||||||
| VoteNet ||||||||
| H3DNet ||||||||
| 3DSSD ||||||||
| Part-A2 ||||||||
| MVXNet ||||||||
| CenterPoint ||||||||
| SSN ||||||||
| ImVoteNet ||||||||
| FCOS3D ||||||||
| PointNet++ ||||||||
| Group-Free-3D ||||||||
| ImVoxelNet ||||||||
| PAConv ||||||||
| DGCNN ||||||||
| SMOKE ||||||||
| PGD ||||||||
| MonoFlex ||||||||
| SA-SSD ||||||||
| FCAF3D ||||||||
| PV-RCNN ||||||||
| | ResNet | PointNet++ | SECOND | DGCNN | RegNetX | DLA | MinkResNet | Cylinder3D |
| :-----------: | :----: | :--------: | :----: | :---: | :-----: | :-: | :--------: | :--------: |
| SECOND |||||||||
| PointPillars |||||||||
| FreeAnchor |||||||||
| VoteNet |||||||||
| H3DNet |||||||||
| 3DSSD |||||||||
| Part-A2 |||||||||
| MVXNet |||||||||
| CenterPoint |||||||||
| SSN |||||||||
| ImVoteNet |||||||||
| FCOS3D |||||||||
| PointNet++ |||||||||
| Group-Free-3D |||||||||
| ImVoxelNet |||||||||
| PAConv |||||||||
| DGCNN |||||||||
| SMOKE |||||||||
| PGD |||||||||
| MonoFlex |||||||||
| SA-SSD |||||||||
| FCAF3D |||||||||
| PV-RCNN |||||||||
| Cylinder3D |||||||||

**注意:**[MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/model_zoo.md) 支持的基于 2D 检测的 **300+ 个模型,40+ 的论文算法**在 MMDetection3D 中都可以被训练或使用。

Expand Down
35 changes: 35 additions & 0 deletions configs/cylinder3d/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
# Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

> [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://arxiv.org/abs/2011.10033)
<!-- [ALGORITHM] -->

## Abstract

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern while maintaining these inherent properties. Moreover, a point-wise refinement module is introduced to alleviate the interference of lossy voxel-based label encoding. We evaluate the proposed model on two large-scale datasets, i.e., SemanticKITTI and nuScenes. Our method achieves the 1st place in the leaderboard of SemanticKITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%. Furthermore, the proposed 3D framework also generalizes well to LiDAR panoptic segmentation and LiDAR 3D detection.

## Introduction

We implement Cylinder3D and provide the result and checkpoints on Semantickitti datasets.

## Results and models

### SemanticKITTI

| Method | Lr schd | Mem (GB) | mIOU | Download |
| :--------: | :-----: | :------: | :------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| Cylinder3D | 3x | 10.2 | 63.1±0.5 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107.json) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107-822a8c31.pth) |

Note: We reproduce the performance comparable with its official repo (https://github.com/xinge008/Cylinder3D). It's slightly lower than the performance (65.9 mIOU) reported in the paper due to the lack of point-wise refinement and shorter training time.

## Citation

```latex
@inproceedings{zhu2021cylindrical,
title={Cylindrical and asymmetrical 3d convolution networks for lidar segmentation},
author={Zhu, Xinge and Zhou, Hui and Wang, Tai and Hong, Fangzhou and Ma, Yuexin and Li, Wei and Li, Hongsheng and Lin, Dahua},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={9939--9948},
year={2021}
}
```
29 changes: 29 additions & 0 deletions configs/cylinder3d/metafile.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
Collections:
- Name: Cylinder3D
Metadata:
Training Techniques:
- AdamW
Training Resources: 4x A100 GPUs
Architecture:
- Cylinder3D
Paper:
URL: https://arxiv.org/abs/2011.10033
Title: 'Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation'
README: configs/cylinder3d/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/mmdet3d/models/segmentors/cylinder3d.py#L13
Version: v1.1.0rc4

Models:
- Name:
In Collection: Cylinder3D
Config: configs/cylinder3d/cylinder3d_4xb4_3x_semantickitti.py
Metadata:
Training Data: SemanticKITTI
Training Memory (GB): 10.2
Results:
- Task: 3D Semantic Segmentation
Dataset: SemanticKITTI
Metrics:
mIOU: 63.1
Weights:
2 changes: 1 addition & 1 deletion mmdet3d/datasets/semantickitti_dataset.py
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ class SemanticKittiDataset(Seg3DDataset):
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
data_prefix (dict): Prefix for training data. Defaults to
dict(pts='points',
dict(pts='',
img='',
pts_instance_mask='',
pts_semantic_mask='').
Expand Down
1 change: 1 addition & 0 deletions model-index.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,5 +23,6 @@ Import:
- configs/smoke/metafile.yml
- configs/ssn/metafile.yml
- configs/votenet/metafile.yml
- configs/cylinder3d/metafile.yml
- configs/pv_rcnn/metafile.yml
- configs/fcaf3d/metafile.yml

0 comments on commit 8475203

Please sign in to comment.