https://github.com/rasd3/3D-CVF

[ECCV 2020] This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection
https://github.com/rasd3/3D-CVF

Last synced: about 2 months ago
JSON representation

[ECCV 2020] This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection

• Host: GitHub
• URL: https://github.com/rasd3/3D-CVF
• Owner: rasd3
• Created: 2020-03-08T07:59:15.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2021-12-01T08:34:36.000Z (about 3 years ago)
• Last Synced: 2024-08-01T03:43:54.234Z (4 months ago)
• Language: Python
• Homepage:
• Size: 2.41 MB
• Stars: 119
• Watchers: 16
• Forks: 22
• Open Issues: 17
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-BEV-Perception - project

README

        
# 3D-CVF

This is the official implementation of [3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection](https://arxiv.org/abs/2004.12636), built on [SECOND](https://github.com/traveller59/second.pytorch).

## Requirements

Follow the installation steps in [SECOND](https://github.com/traveller59/second.pytorch), or use the docker image we provide.

```

docker pull yckimm/second:second_v1.5

```

## Getting Started

### Training (1st stage)

```

sh train_bash_1st.sh

```

### Training (2nd stage)

```

sh train_bash_2nd.sh

```

## Acknowledge

Thanks to the [SECOND](https://github.com/traveller59/second.pytorch) codebase maintained by traveller59.