# DRIFT: Dual-Representation Inter-Fusion Transformer for Automated Driving Perception with 4D Radar Point Clouds

arXiv: https://arxiv.org/abs/2603.09695 · HTML: https://mlsanity.com/paper/2603.09695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar](https://mlsanity.com/paper/2307.10784/) (2023)
- [PVT: Point-Voxel Transformer for Point Cloud Learning](https://mlsanity.com/paper/2108.06076/) (2021)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [RadarPillars: Efficient Object Detection from 4D Radar Point Clouds](https://mlsanity.com/paper/2408.05020/) (2024)
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://mlsanity.com/paper/2108.04023/) (2021)
- [Deep Instance Segmentation with Automotive Radar Detection Points](https://mlsanity.com/paper/2110.01775/) (2021)
- [MVFAN: Multi-View Feature Assisted Network for 4D Radar Object Detection](https://mlsanity.com/paper/2310.16389/) (2023)
- [MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detection](https://mlsanity.com/paper/2408.00565/) (2024)
- [PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection](https://mlsanity.com/paper/2405.02811/) (2024)

## Abstract (arXiv)

4D radars, which provide 3D point cloud data along with Doppler velocity, are attractive components of modern automated driving systems due to their low cost and robustness under adverse weather conditions. However, they provide a significantly lower point cloud density than LiDAR sensors. This makes it important to exploit not only local but also global contextual scene information. This paper proposes DRIFT, a model that effectively captures and fuses both local and global contexts through a dual-path architecture. The model incorporates a point path to aggregate fine-grained local features and a pillar path to encode coarse-grained global features. These two parallel paths are intertwined via novel feature-sharing layers at multiple stages, enabling full utilization of both representations. DRIFT is evaluated on the widely used View-of-Delft (VoD) dataset and a proprietary internal dataset. It outperforms the baselines on the tasks of object detection and/or free road estimation. For example, DRIFT achieves a mean average precision (mAP) of 52.6% (compared to, say, 45.4% of CenterPoint) on the VoD dataset.