RiO-DETR: DETR for Real-time Oriented Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908876205457408 |
|---|---|
| author | Hu, Zhangchi Zhao, Yifan Peng, Yansong Sun, Wenzhang Yin, Xiangchen Chen, Jie Wu, Peixi Li, Hebei Wang, Xinghao Jiang, Dongsheng Sun, Xiaoyan |
| author_facet | Hu, Zhangchi Zhao, Yifan Peng, Yansong Sun, Wenzhang Yin, Xiangchen Chen, Jie Wu, Peixi Li, Hebei Wang, Xinghao Jiang, Dongsheng Sun, Xiaoyan |
| contents | We present RiO-DETR: DETR for Real-time Oriented Object Detection, the first real-time oriented detection transformer to the best of our knowledge. Adapting DETR to oriented bounding boxes (OBBs) poses three challenges: semantics-dependent orientation, angle periodicity that breaks standard Euclidean refinement, and an enlarged search space that slows convergence. RiO-DETR resolves these issues with task-native designs while preserving real-time efficiency. First, we propose Content-Driven Angle Estimation by decoupling angle from positional queries, together with Rotation-Rectified Orthogonal Attention to capture complementary cues for reliable orientation. Second, Decoupled Periodic Refinement combines bounded coarse-to-fine updates with a Shortest-Path Periodic Loss for stable learning across angular seams. Third, Oriented Dense O2O injects angular diversity into dense supervision to speed up angle convergence at no extra cost. Extensive experiments on DOTA-1.0, DIOR-R, and FAIR-1M-2.0 demonstrate RiO-DETR establishes a new speed--accuracy trade-off for real-time oriented detection. Code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09411 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RiO-DETR: DETR for Real-time Oriented Object Detection Hu, Zhangchi Zhao, Yifan Peng, Yansong Sun, Wenzhang Yin, Xiangchen Chen, Jie Wu, Peixi Li, Hebei Wang, Xinghao Jiang, Dongsheng Sun, Xiaoyan Computer Vision and Pattern Recognition We present RiO-DETR: DETR for Real-time Oriented Object Detection, the first real-time oriented detection transformer to the best of our knowledge. Adapting DETR to oriented bounding boxes (OBBs) poses three challenges: semantics-dependent orientation, angle periodicity that breaks standard Euclidean refinement, and an enlarged search space that slows convergence. RiO-DETR resolves these issues with task-native designs while preserving real-time efficiency. First, we propose Content-Driven Angle Estimation by decoupling angle from positional queries, together with Rotation-Rectified Orthogonal Attention to capture complementary cues for reliable orientation. Second, Decoupled Periodic Refinement combines bounded coarse-to-fine updates with a Shortest-Path Periodic Loss for stable learning across angular seams. Third, Oriented Dense O2O injects angular diversity into dense supervision to speed up angle convergence at no extra cost. Extensive experiments on DOTA-1.0, DIOR-R, and FAIR-1M-2.0 demonstrate RiO-DETR establishes a new speed--accuracy trade-off for real-time oriented detection. Code will be made publicly available. |
| title | RiO-DETR: DETR for Real-time Oriented Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09411 |