---
license: apache-2.0
library_name: OpenPCDet
pipeline_tag: object-detection
tags:
- 3d-object-detection
- 4d-radar
- radar-perception
- autonomous-driving
- pointpillars
- openpcdet
- view-of-delft
datasets:
- view-of-delft
metrics:
- mAP
---

# RadarPillars — View-of-Delft (radar-only 3D object detection)

Radar-only 3D object detection on the **View-of-Delft (VoD)** dataset — an OpenPCDet-based reproduction of **RadarPillars** ([Musiat et al., IROS 2024](https://arxiv.org/abs/2408.05020)). This checkpoint **reproduces and exceeds** the published result using 4D radar point clouds only (no camera, no LiDAR).

- 📄 Paper: https://arxiv.org/abs/2408.05020
- 💻 Code, configs & full ablation: https://github.com/fthbng77/RadarPillar

## Results (mAP_3D, R11)

| Method | Car @ 0.50 | Ped @ 0.25 | Cyc @ 0.25 | mAP_3D |
|---|:---:|:---:|:---:|:---:|
| **This checkpoint (best seed, s3)** | **41.58** | **44.78** | 71.31 | **52.56** |
| 3-seed mean | 41.02 | 43.15 | 70.12 | 51.43 ± 0.99 |
| RadarPillars (paper) | 41.10 | 38.60 | 72.60 | 50.70 |

**+1.86 mAP_3D over the paper** (best seed). Checkpoint: seed s3 @ epoch 60 (eval-best).

## Usage

```bash
git clone https://github.com/fthbng77/RadarPillar
cd RadarPillar
python setup.py develop

# download this checkpoint
huggingface-cli download fthbng77/radarpillars-vod radarpillar_vod_best_map52.56.pth --local-dir weights

# evaluate
python tools/test.py \
  --cfg_file tools/cfgs/vod_models/vod_radarpillar_rot.yaml \
  --ckpt weights/radarpillar_vod_best_map52.56.pth
```

## Architecture

PillarVFE (radial-velocity decomposition) → PillarAttention (masked self-attention) → PointPillarScatter → BaseBEVBackbone → AnchorHeadSingle (Car / Pedestrian / Cyclist). ~0.27M params. See the [GitHub repo](https://github.com/fthbng77/RadarPillar) for full details.

## Citation

```bibtex
@inproceedings{radarpillars2024,
  title     = {RadarPillars: Efficient Object Detection from 4D Radar Point Clouds},
  author    = {Musiat, Alexander and Reichardt, Laurenz and Schulze, Michael and Wasenm{\"u}ller, Oliver},
  booktitle = {Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS)},
  year      = {2024}
}
```

License: Apache-2.0. Built on [OpenPCDet](https://github.com/open-mmlab/OpenPCDet).