# RCDPT: Radar-Camera fusion Dense Prediction Transformer

arXiv: https://arxiv.org/abs/2211.02432 · HTML: https://mlsanity.com/paper/2211.02432/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 4 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image](https://mlsanity.com/paper/1709.07492/) (2017)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [Sparse and noisy LiDAR completion with RGB guidance and uncertainty](https://mlsanity.com/paper/1902.05356/) (2019)
- [Radar-Camera Pixel Depth Association for Depth Completion](https://mlsanity.com/paper/2106.02778/) (2021)
- [Depth Estimation from Monocular Images and Sparse Radar Data](https://mlsanity.com/paper/2010.00058/) (2020)
- [Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Network](https://mlsanity.com/paper/2107.07596/) (2021)

## Built on by (most cited first, 8 of 8)

- [CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation](https://mlsanity.com/paper/2407.00697/) (2024)
- [MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources](https://mlsanity.com/paper/2601.22054/) (2026)
- [TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion](https://mlsanity.com/paper/2504.11773/) (2025)
- [GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling](https://mlsanity.com/paper/2409.02720/) (2024)
- [Structure-Aware Radar-Camera Depth Estimation](https://mlsanity.com/paper/2506.05008/) (2025)
- [JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision](https://mlsanity.com/paper/2607.22172/) (2026)
- [Instance-Guided Radar Depth Estimation for 3D Object Detection](https://mlsanity.com/paper/2601.19314/) (2026)
- [Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2610.16012/) (2026)

## Abstract (arXiv)

Recently, transformer networks have outperformed traditional deep neural networks in natural language processing and show a large potential in many computer vision tasks compared to convolutional backbones. In the original transformer, readout tokens are used as designated vectors for aggregating information from other tokens. However, the performance of using readout tokens in a vision transformer is limited. Therefore, we propose a novel fusion strategy to integrate radar data into a dense prediction transformer network by reassembling camera representations with radar representations. Instead of using readout tokens, radar representations contribute additional depth information to a monocular depth estimation model and improve performance. We further investigate different fusion approaches that are commonly used for integrating additional modality in a dense prediction transformer network. The experiments are conducted on the nuScenes dataset, which includes camera images, lidar, and radar data. The results show that our proposed method yields better performance than the commonly used fusion strategies and outperforms existing convolutional depth estimation models that fuse camera images and radar.