RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916165252546560 |
|---|---|
| author | Li, Han Ma, Yukai Gu, Yaqing Hu, Kewei Liu, Yong Zuo, Xingxing |
| author_facet | Li, Han Ma, Yukai Gu, Yaqing Hu, Kewei Liu, Yong Zuo, Xingxing |
| contents | We present a novel approach for metric dense depth estimation based on the fusion of a single-view image and a sparse, noisy Radar point cloud. The direct fusion of heterogeneous Radar and image data, or their encodings, tends to yield dense depth maps with significant artifacts, blurred boundaries, and suboptimal accuracy. To circumvent this issue, we learn to augment versatile and robust monocular depth prediction with the dense metric scale induced from sparse and noisy Radar data. We propose a Radar-Camera framework for highly accurate and fine-detailed dense depth estimation with four stages, including monocular depth prediction, global scale alignment of monocular depth with sparse Radar points, quasi-dense scale estimation through learning the association between Radar points and image patches, and local scale refinement of dense depth using a scale map learner. Our proposed method significantly outperforms the state-of-the-art Radar-Camera depth estimation methods by reducing the mean absolute error (MAE) of depth estimation by 25.6% and 40.2% on the challenging nuScenes dataset and our self-collected ZJU-4DRadarCam dataset, respectively. Our code and dataset will be released at \url{https://github.com/MMOCKING/RadarCam-Depth}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04325 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale Li, Han Ma, Yukai Gu, Yaqing Hu, Kewei Liu, Yong Zuo, Xingxing Computer Vision and Pattern Recognition We present a novel approach for metric dense depth estimation based on the fusion of a single-view image and a sparse, noisy Radar point cloud. The direct fusion of heterogeneous Radar and image data, or their encodings, tends to yield dense depth maps with significant artifacts, blurred boundaries, and suboptimal accuracy. To circumvent this issue, we learn to augment versatile and robust monocular depth prediction with the dense metric scale induced from sparse and noisy Radar data. We propose a Radar-Camera framework for highly accurate and fine-detailed dense depth estimation with four stages, including monocular depth prediction, global scale alignment of monocular depth with sparse Radar points, quasi-dense scale estimation through learning the association between Radar points and image patches, and local scale refinement of dense depth using a scale map learner. Our proposed method significantly outperforms the state-of-the-art Radar-Camera depth estimation methods by reducing the mean absolute error (MAE) of depth estimation by 25.6% and 40.2% on the challenging nuScenes dataset and our self-collected ZJU-4DRadarCam dataset, respectively. Our code and dataset will be released at \url{https://github.com/MMOCKING/RadarCam-Depth}. |
| title | RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.04325 |