mlsanityData to 7 Oct 2026

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

arXiv 2603.09411 ↗First posted 10 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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. GitHub Repository: https://github.com/RicePasteM/RiO-DETR.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

53 of 67 references.

References · 53

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  5. 2015Fast R-CNNcited by 2,930
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  9. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  10. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  11. 2019Object Detection in 20 Years: A Surveycited by 528
  12. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
38 more
  1. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  2. 2021Conditional DETR for Fast Training Convergencecited by 422
  3. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
  4. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  5. 2021Oriented R-CNN for Object Detectioncited by 230
  6. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  7. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  8. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  9. 2020Align Deep Features for Oriented Object Detectioncited by 186
  10. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  11. 2022Advancing Plain Vision Transformer Towards Remote Sensing Foundation Modelcited by 149
  12. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  13. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  14. 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
  15. 2021Anchor-free Oriented Proposal Generator for Object Detectioncited by 104
  16. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  17. 2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 88
  18. 2025YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detectioncited by 76
  19. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  20. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  21. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  22. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  23. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  24. 2020PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environmentscited by 56
  25. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  26. 2024Poly Kernel Inception Network for Remote Sensing Detectioncited by 52
  27. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  28. 2023Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detectioncited by 43
  29. 2024LW-DETR: A Transformer Replacement to YOLO for Real-Time Detectioncited by 36
  30. 2023ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detectioncited by 32
  31. 2024RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervisioncited by 31
  32. 2025Real-Time Object Detection Meets DINOv3cited by 26
  33. 2024GRPose: Learning Graph Relations for Human Image Generation with Pose Priorscited by 14
  34. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  35. 2025RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Modelscited by 13
  36. 2023Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformercited by 9
  37. 2025MotionStrata: Hierarchical Motion Latents for Compact Video Autoencodingcited by 9
  38. 2024Projecting Points to Axes: Oriented Object Detection via Point-Axis Representationcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026GTR: Gated Token Recurrence for Efficient Dense Predictioncited by 0