RiO-DETR: DETR for Real-time Oriented Object Detection

TL;DR

RiO-DETR is a novel real-time oriented object detection transformer that effectively handles orientation challenges, achieving a superior speed-accuracy balance on multiple datasets.

Contribution

It introduces task-native designs for oriented detection, including angle estimation, periodic refinement, and angular diversity, enabling real-time performance.

Findings

Outperforms existing methods in speed and accuracy on DOTA-1.0, DIOR-R, and FAIR-1M-2.0 datasets.

Achieves real-time detection with high accuracy for oriented objects.

Demonstrates effective handling of orientation challenges in transformer-based detection.

Abstract

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.