ECCV 2026 Oral｜中科大&华为提出RiO-DETR：首个端到端实时DETR旋转检测模型
Ranking
Overall
68
Content
80
Popularity
39
Observed public metrics from 1 member.
Merged summary
TL;DR - RiO-DETR is an ECCV 2026 Oral paper introducing an end-to-end, real-time DETR model for oriented object detection. It matches YOLO-like latency while improving accuracy and eliminating NMS.
- Separates angle estimation from geometric position queries, using visual content and orthogonal attention to capture object orientation.
- Introduces periodic angle refinement and shortest-path loss to handle angular wraparound and stabilize decoder updates.
- Uses Oriented Dense O2O training to increase orientation diversity and accelerate convergence without inference overhead.
- On DOTA-1.0, models range from 2.7 ms/78.4 AP50 to 29.9 ms/81.8 AP50 on an NVIDIA T4 with TensorRT 10 and FP16.
Sources (1)
ECCV 2026 Oral｜中科大&华为提出RiO-DETR：首个端到端实时DETR旋转检测模型
Public signals
Hugging Face upvotes 0
TL;DR - RiO-DETR is an ECCV 2026 Oral paper introducing an end-to-end, real-time DETR model for oriented object detection. It matches YOLO-like latency while improving accuracy and eliminating NMS.
- Separates angle estimation from geometric position queries, using visual content and orthogonal attention to capture object orientation.
- Introduces periodic angle refinement and shortest-path loss to handle angular wraparound and stabilize decoder updates.
- Uses Oriented Dense O2O training to increase orientation diversity and accelerate convergence without inference overhead.
- On DOTA-1.0, models range from 2.7 ms/78.4 AP50 to 29.9 ms/81.8 AP50 on an NVIDIA T4 with TensorRT 10 and FP16.