update README.md

README.md

-# OpenLidarPerceptron
+<img src="docs/open_mmlab.png" align="right" width="30%">
+
+# OpenPCDet
 
 ## Introduction
-`OpenLidarPerceptron` is an open source project for LiDAR-based 3D scene perception. 
-As of now, it mainly consists of `PCDet` toolbox for 3D object detection from point cloud, 
-and we are going to support LiDAR segmentation and odometry in the next phase.
+`OpenPCDet` is an open source project for LiDAR-based 3D scene perception. 
+As of now, it mainly consists of `PCDet` toolbox for 3D object detection from point cloud.
 
 
 ### What does `PCDet` toolbox do?
@@ -22,9 +23,21 @@ It is also the official code release of [`[Part-A^2 net]`](https://arxiv.org/abs
 We are actively updating this repo currently, and more datasets and models will be supported soon. 
 Contributions are also welcomed. 
 
+### `PCDet` design pattern
+
+* Data-Model separation with unified point cloud coordinate for easily extending to custom datasets: 
+<p align="center">
+  <img src="docs/dataset_vs_model.png" width="95%" height="320">
+</p>
+
+* Flexible and clear model structure to easily support various 3D detection models: 
+<p align="center">
+  <img src="docs/model_framework.png" width="95%">
+</p>
+
 
 ### Currently Supported Features
-- [x] Unified point cloud coordinate and clear code structure and for supporting lots of datasets and approaches
+
 - [x] Support both one-stage and two-stage 3D object detection frameworks
 - [x] Support distributed training & testing with multiple GPUs and multiple machines
 - [x] Support multiple heads on different scales to detect different classes
@@ -33,6 +46,7 @@ Contributions are also welcomed.
 - [x] Support RoI-aware point cloud pooling & RoI-grid point cloud pooling
 - [x] Support GPU version 3D IoU calculation and rotated NMS 
 
+
 ## Model Zoo
 
 ### KITTI 3D Object Detection Baselines
@@ -48,6 +62,9 @@ All models are trained with 8 GPUs and are available for download.
 | [SECOND-MultiHead](tools/cfgs/kitti_models/second_multihead.yaml) | 32 | - | - | - | ongoing |
 | PointRCNN | 32 | - | - | - | ongoing|
 
+### Other datasets
+More datasets are on the way. 
+
 ## Installation
 
 Please refer to [INSTALL.md](docs/INSTALL.md) for installation and dataset preparation.
@@ -59,10 +76,10 @@ Please refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md) to learn more usag
 
 ## License
 
-`OpenLidarPerceptron` is released under the [Apache 2.0 license](LICENSE).
+`OpenPCDet` is released under the [Apache 2.0 license](LICENSE).
 
 ## Acknowledgement
-`OpenLidarPerceptron` is an open source project for LiDAR-based 3D scene perception that supports multiple
+`OpenPCDet` is an open source project for LiDAR-based 3D scene perception that supports multiple
 LiDAR-based perception models as shown above. Some parts of `PCDet` are learned from the official released codes of the above supported methods. 
 We would like to thank for their proposed methods and the official implementation.   
 

docs/INSTALL.md

@@ -14,7 +14,7 @@ NOTE: Please re-install `pcdet v0.2` by running `python setup.py develop` if you
 
 a. Clone this repository.
 ```shell
-git clone https://github.com/open-mmlab/OpenLidarPerceptron.git
+git clone https://github.com/open-mmlab/OpenPCDet.git
 ```
 
 b. Install the dependent libraries as follows:

pcdet/datasets/augmentor/data_augmentor.py

@@ -46,7 +46,6 @@ class DataAugmentor(object):
         data_dict['points'] = points
         return data_dict
 
-   
     def random_world_rotation(self, data_dict=None, config=None):
         if data_dict is None:
             return partial(self.random_world_rotation, config=config)
@@ -61,7 +60,6 @@ class DataAugmentor(object):
         data_dict['points'] = points
         return data_dict
 
- 
     def random_world_scaling(self, data_dict=None, config=None):
         if data_dict is None:
             return partial(self.random_world_scaling, config=config)

pcdet/datasets/processor/data_processor.py

@@ -14,7 +14,6 @@ class DataProcessor(object):
             cur_processor = getattr(self, cur_cfg.NAME)(config=cur_cfg)
             self.data_processor_queue.append(cur_processor)
 
- 
     def mask_points_and_boxes_outside_range(self, data_dict=None, config=None):
         if data_dict is None:
             return partial(self.mask_points_and_boxes_outside_range, config=config)

setup.py

@@ -33,7 +33,7 @@ if __name__ == '__main__':
     setup(
         name='pcdet',
         version=version,
-        description='PCDet is a general codebase for 3D object detection from point cloud',
+        description='OpenPCDet is a general codebase for 3D object detection from point cloud',
         install_requires=[
             'numpy',
             'torch>=1.1',