RiO-DETRv2
RiO-DETRv2 is a real-time oriented-box DETR. It predicts four box sides as distributions in the box's own frame, refines the angle coarse to fine and scores each box with an angle-aware quality. LibreYOLO ports it inference-only, in five sizes, with DOTA-v1.0 and DIOR-R checkpoints.
- Tasks
- oriented boxes
- Install
pip install libreyolo- Support tier
- Inference only, since v1.8.0. Predict, validate and export only. Training features do not apply.
- Licenses
- Code Apache-2.0, weights Apache-2.0. Commercial use
Install
RiO-DETRv2 needs no optional extra.
pip install libreyoloPredict
Weights download from the LibreYOLO Hugging Face mirrors on first use. The models are trained on aerial imagery, so use an overhead photo.
from libreyolo import LibreYOLO model = LibreYOLO("LibreRiODETRv2s-obb.pt") # DOTA-v1.0, 15 classesresult = model("aerial.jpg", save=True) print(result.obb.xywhr) # (N, 5) centre, size and angleprint(result.obb.conf, result.obb.cls)from libreyolo import LibreYOLO model = LibreYOLO("LibreRiODETRv2s-obb-diorr.pt") # DIOR-R, 20 classesresult = model("aerial.jpg")libreyolo predict model=LibreRiODETRv2s-obb.pt source=aerial.jpg save=Trueresult.obb holds the rotated boxes: xywhr (centre, width, height and
angle), conf and cls, with class names from the checkpoint. See the
oriented detection task page for the
payload and plotting.
Variants
Five sizes, n, s, m, l and x, each with two checkpoints:
| Checkpoint | Dataset | Classes | Canvas |
|---|---|---|---|
LibreRiODETRv2<size>-obb.pt | DOTA-v1.0 | 15 | 1024 px |
LibreRiODETRv2<size>-obb-diorr.pt | DIOR-R | 20 | 800 px |
The native canvas is read from the checkpoint. Raw outputs and decoded rotated boxes match the upstream Apache-2.0 release exactly (max absolute difference 0) for all ten checkpoints on CPU.
RiO-DETRv2 is inference-only. train() raises: the upstream recipe (DINOv3
feature distillation, OBB Hungarian matching, boundary and angle
distribution losses) is not ported. For trainable oriented-box detection use
GTR or YOLO-NAS.
Export
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Oriented boxes | Oriented boxes to ONNX: supported | Oriented boxes to TorchScript: supported | Oriented boxes to ExecuTorch: supported | Oriented boxes to TensorRT: supported | Oriented boxes to OpenVINO: supported | Oriented boxes to Paddle: not supported | Oriented boxes to MNN: not supported | Oriented boxes to RKNN: not supported | Oriented boxes to Axelera: not supported | Oriented boxes to ncnn: not supported | Oriented boxes to TFLite: not supported | Oriented boxes to CoreML: not supported | Oriented boxes to Core AI: not supported |
ONNX and TorchScript exports round-trip: the exported file loads back through
LibreYOLO() and returns the same Results.
from libreyolo import LibreYOLO model = LibreYOLO("LibreRiODETRv2s-obb.pt")model.export(format="onnx")model.export(format="torchscript")libreyolo export model=LibreRiODETRv2s-obb.pt format=onnxCheckpoints
| File | Weights license |
|---|---|
| Oriented boxes | |
| LibreRiODETRv2l-obb.pt | apache-2.0 |
| LibreRiODETRv2l-obb-diorr.pt | apache-2.0 |
| LibreRiODETRv2m-obb.pt | apache-2.0 |
| LibreRiODETRv2m-obb-diorr.pt | apache-2.0 |
| LibreRiODETRv2n-obb.pt | apache-2.0 |
| LibreRiODETRv2n-obb-diorr.pt | apache-2.0 |
| LibreRiODETRv2s-obb.pt | apache-2.0 |
| LibreRiODETRv2s-obb-diorr.pt | apache-2.0 |
| LibreRiODETRv2x-obb.pt | apache-2.0 |
| LibreRiODETRv2x-obb-diorr.pt | apache-2.0 |
Every file above exists in the LibreYOLO org today and downloads on first use.
Licensing
Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.
This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.
- Original work
- RiO-DETRv2, RiO-DETRv2 authors (RicePasteM)
- Upstream license
- Apache-2.0
- Upstream source
- github.com/RicePasteM/RiO-DETRv2
- LibreYOLO code
- MIT
- Weights
- Apache-2.0, republished at huggingface.co/LibreYOLO
- Interpretation
- Apache-2.0 is a permissive license, so the RiO-DETRv2 code and checkpoints can be used in commercial and closed-source products. Redistributing them means keeping the license text and notices, and the license grants a patent license. About 33 minutes after its initial commit (ab8b22df5d800a927774c8c67e77fd29c0fe6967), upstream changed its LICENSE file to AGPL-3.0; later commits change only the README and LICENSE, not the code. LibreYOLO's port relies on the Apache-2.0 grant of that initial release, uses nothing from later commits, and preserves the Apache-2.0 snapshot at LibreYOLO/RiO-DETRv2 (tag apache-2.0-ab8b22d). The adapted decoder keeps Apache-2.0 with its RT-DETR, D-FINE, DEIM and RT-DETRv4 copyright lines (libreyolo/models/riodetrv2/LICENSE and NOTICE); the HGNetv2 backbone, encoder and decoder blocks reuse LibreYOLO's dfine and rtdetrv2 families, and the wiring around them is LibreYOLO's MIT code. The official checkpoints (Hugging Face RicePasteM/RiO-DETRv2 at revision 5f578f57929aded1962ebf8c5584a4771461124f, tagged apache-2.0) are mirrored as LibreYOLO/LibreRiODETRv2{n,s,m,l,x}-obb (DOTA-v1.0) and -obb-diorr (DIOR-R) with the upstream LICENSE and NOTICE; conversion renames keys and drops a training-only projector, learned tensors are unchanged. The DOTA-v1.0 and DIOR-R training sets carry their own terms.
RiO-DETRv2 is by RicePasteM
(RicePasteM/RiO-DETRv2). Code and
weights are Apache-2.0, so commercial use is fine. Upstream changed its
LICENSE file to AGPL-3.0 about 33 minutes after its initial commit, with no
code changes. LibreYOLO's port uses only that initial Apache-2.0 release
(commit ab8b22d) and preserves the snapshot at LibreYOLO/RiO-DETRv2. The
official checkpoints are mirrored as LibreYOLO/LibreRiODETRv2{n,s,m,l,x}-obb
and -obb-diorr, with keys renamed and learned tensors unchanged. The
DOTA-v1.0 and DIOR-R training sets carry their own terms.
Citation
@misc{hu2026riodetrv2geometryawareuncertaintymodeling,
title={RiO-DETRv2: Geometry-Aware Uncertainty Modeling Meets Real-Time Oriented Object Detection Transformer},
author={Zhangchi Hu and Zilong He and Yifan Zhao and Xiangyu Yu and Jie Chen and Peixi Wu and Yansong Peng and Hebei Li and Xiaoyan Sun},
year={2026},
eprint={2610.29159},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2610.29159},
}Copied from the authors' citation block at arxiv.org/bibtex/2610.29159.