RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915373119438848 |
|---|---|
| author | Qin, Xingrui Zhao, Wentao Cao, Chuan Niu, Yihe Deng, Tianchen Jiang, Houcheng Guo, Rui Wang, Jingchuan |
| author_facet | Qin, Xingrui Zhao, Wentao Cao, Chuan Niu, Yihe Deng, Tianchen Jiang, Houcheng Guo, Rui Wang, Jingchuan |
| contents | Dense depth estimation using millimeter-wave radar typically requires dense LiDAR supervision, generated via multi-frame projection and interpolation, for guiding the learning of accurate depth from sparse radar measurements and RGB images. However, this paradigm is both costly and data-intensive. To address this, we propose RaCalNet, a novel framework that eliminates the need for dense supervision by using sparse LiDAR to supervise the learning of refined radar measurements, resulting in a supervision density of merely around 1\% compared to dense-supervised methods. RaCalNet is composed of two key modules. The Radar Recalibration module performs radar point screening and pixel-wise displacement refinement, producing accurate and reliable depth priors from sparse radar inputs. These priors are then used by the Metric Depth Optimization module, which learns to infer scene-level scale priors and fuses them with monocular depth predictions to achieve metrically accurate outputs. This modular design enhances structural consistency and preserves fine-grained geometric details. Despite relying solely on sparse supervision, RaCalNet produces depth maps with clear object contours and fine-grained textures, demonstrating superior visual quality compared to state-of-the-art dense-supervised methods. Quantitatively, it achieves performance comparable to existing methods on the ZJU-4DRadarCam dataset and yields a 34.89\% RMSE reduction in real-world deployment scenarios. We plan to gradually release the code and models in the future at https://github.com/818slam/RaCalNet.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation Qin, Xingrui Zhao, Wentao Cao, Chuan Niu, Yihe Deng, Tianchen Jiang, Houcheng Guo, Rui Wang, Jingchuan Computer Vision and Pattern Recognition Robotics Dense depth estimation using millimeter-wave radar typically requires dense LiDAR supervision, generated via multi-frame projection and interpolation, for guiding the learning of accurate depth from sparse radar measurements and RGB images. However, this paradigm is both costly and data-intensive. To address this, we propose RaCalNet, a novel framework that eliminates the need for dense supervision by using sparse LiDAR to supervise the learning of refined radar measurements, resulting in a supervision density of merely around 1\% compared to dense-supervised methods. RaCalNet is composed of two key modules. The Radar Recalibration module performs radar point screening and pixel-wise displacement refinement, producing accurate and reliable depth priors from sparse radar inputs. These priors are then used by the Metric Depth Optimization module, which learns to infer scene-level scale priors and fuses them with monocular depth predictions to achieve metrically accurate outputs. This modular design enhances structural consistency and preserves fine-grained geometric details. Despite relying solely on sparse supervision, RaCalNet produces depth maps with clear object contours and fine-grained textures, demonstrating superior visual quality compared to state-of-the-art dense-supervised methods. Quantitatively, it achieves performance comparable to existing methods on the ZJU-4DRadarCam dataset and yields a 34.89\% RMSE reduction in real-world deployment scenarios. We plan to gradually release the code and models in the future at https://github.com/818slam/RaCalNet.git. |
| title | RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2506.15560 |