CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912969252667392 |
|---|---|
| author | Kegl, Marcell Palffy, Andras Benedek, Csaba Gavrila, Dariu M. |
| author_facet | Kegl, Marcell Palffy, Andras Benedek, Csaba Gavrila, Dariu M. |
| contents | In this paper, we address extrinsic calibration for camera, lidar, and 4D radar sensors. Accurate extrinsic calibration of radar remains a challenge due to the sparsity of its data. We propose CLRNet, a novel, multi-modal end-to-end deep learning (DL) calibration network capable of addressing joint camera-lidar-radar calibration, or pairwise calibration between any two of these sensors. We incorporate equirectangular projection, camera-based depth image prediction, additional radar channels, and leverage lidar with a shared feature space and loop closure loss. In extensive experiments using the View-of-Delft and Dual-Radar datasets, we demonstrate superior calibration accuracy compared to existing state-of-the-art methods, reducing both median translational and rotational calibration errors by at least 50%. Finally, we examine the domain transfer capabilities of the proposed network and baselines, when evaluating across datasets. The code will be made publicly available upon acceptance at: https://github.com/tudelft-iv. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15767 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning Kegl, Marcell Palffy, Andras Benedek, Csaba Gavrila, Dariu M. Computer Vision and Pattern Recognition In this paper, we address extrinsic calibration for camera, lidar, and 4D radar sensors. Accurate extrinsic calibration of radar remains a challenge due to the sparsity of its data. We propose CLRNet, a novel, multi-modal end-to-end deep learning (DL) calibration network capable of addressing joint camera-lidar-radar calibration, or pairwise calibration between any two of these sensors. We incorporate equirectangular projection, camera-based depth image prediction, additional radar channels, and leverage lidar with a shared feature space and loop closure loss. In extensive experiments using the View-of-Delft and Dual-Radar datasets, we demonstrate superior calibration accuracy compared to existing state-of-the-art methods, reducing both median translational and rotational calibration errors by at least 50%. Finally, we examine the domain transfer capabilities of the proposed network and baselines, when evaluating across datasets. The code will be made publicly available upon acceptance at: https://github.com/tudelft-iv. |
| title | CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.15767 |