InstantHMR

InstantHMR, by Naturalpad and LAAS-CNRS, is a real-time human mesh recovery model. For each person box it returns MHR body pose and identity parameters, 70 keypoints in 2D and 3D, the camera translation and an 18,439-vertex mesh. LibreYOLO ports it natively in PyTorch and finds the people with RF-DETR.

Tâches
body mesh
Installer
pip install libreyolo
Niveau de support
Pris en charge, depuis v1.8.0. Modèles entraînables complémentaires : maintenus au vert dans la CI, avec des fonctionnalités ajoutées selon les occasions.
Origine
InstantHMR par Naturalpad and LAAS-CNRS, CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint). Article, source
Licences
Code Apache-2.0, poids CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial). Usage commercial

Install

InstantHMR needs no optional extra. The default person detector, LibreRFDETRm.pt, needs the RF-DETR extra.

bash
pip install "libreyolo[rfdetr]"

Predict

Weights download from the LibreYOLO Hugging Face mirrors on first use, after a licence notice.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreInstantHMRm-mesh.pt")   # people found with LibreRFDETRm.ptresult = model("people.jpg") meshes = result.meshes            # one row per box in result.boxesprint(meshes.body_model)          # "mhr"print(meshes.vertices.shape)      # (people, 18439, 3) metres, camera frameprint(meshes.joints2d.shape)      # (people, 70, 2) pixels
Your own boxes
from libreyolo import LibreYOLO model = LibreYOLO("LibreInstantHMRm-mesh-commercial.pt")boxes = [[40, 20, 260, 600]]      # x1, y1, x2, y2 per personresult = model("people.jpg", person_boxes=boxes)

People are found by an RF-DETR detector (LibreRFDETRm.pt by default). Pass person_boxes= to use your own boxes, or person_detector= to swap the detector. result.meshes rows line up with result.boxes. Everything is in the camera frame of the original image: transl is in metres, vertices and joints3d are metric and include transl, and joints2d is in pixels on the original image. global_orient, body_pose and betas hold the MHR parameters; MHR rotations are Euler angles in radians. See the body mesh task page for the full payload.

Variants

Four sizes, n, t, s and m, all at a 288 px person crop, plus LibreInstantHMRm-mesh-commercial.pt, an m trained only on commercially usable images. Upstream publishes ONNX only; LibreYOLO rebuilds PyTorch checkpoints that match the upstream ONNX graphs within 8e-5 for all five releases.

Train

train() fine-tunes a pretrained checkpoint on a YOLO-pose dataset with COCO-17 person keypoints, using 2D keypoint, reprojection and frozen-prior losses. Training from scratch and resume are not supported. val() raises: the usual body-mesh benchmarks (3DPW, EMDB) are research-license only, so none is bundled; the MPJPE, PA-MPJPE and PVE metrics are in libreyolo.validation.mesh_metrics for a dataset you hold.

Python
from libreyolo import LibreYOLO # Fine-tune a pretrained checkpoint on a YOLO-pose COCO-17 dataset.model = LibreYOLO("LibreInstantHMRs-mesh.pt")model.train(data="my-pose-dataset.yaml", epochs=20)

Export

TâcheONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
Body meshBody mesh to ONNX : pris en chargeBody mesh to TorchScript : non pris en chargeBody mesh to ExecuTorch : non pris en chargeBody mesh to TensorRT : non pris en chargeBody mesh to OpenVINO : non pris en chargeBody mesh to Paddle : non pris en chargeBody mesh to MNN : non pris en chargeBody mesh to RKNN : non pris en chargeBody mesh to Axelera : non pris en chargeBody mesh to ncnn : non pris en chargeBody mesh to TFLite : non pris en chargeBody mesh to CoreML : non pris en chargeBody mesh to Core AI : non pris en charge

export(format="onnx") writes a graph with image and cliff_cond inputs and the mesh faces in its metadata.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreInstantHMRm-mesh.pt")model.export(format="onnx")   # inputs image, cliff_cond; faces in metadata

Checkpoints

FichierLicence des poids
Body mesh
LibreInstantHMRn-mesh.ptcc-by-nc-4.0
LibreInstantHMRt-mesh.ptcc-by-nc-4.0
LibreInstantHMRs-mesh.ptcc-by-nc-4.0
LibreInstantHMRm-mesh.ptcc-by-nc-4.0
LibreInstantHMRm-mesh-commercial.ptapache-2.0

Tous les fichiers ci-dessus sont actuellement disponibles dans l<link>organisation LibreYOLO</link> et sont téléchargés à la première utilisation.

Licensing

Vérifiez la licence dans le dépôt Hugging Face des poids précis que vous téléchargez. Chaque checkpoint de l<link>organisation LibreYOLO</link> en possède une, et elles ne sont pas toujours identiques au sein dune même famille. Ce dépôt fait autorité ; le résumé ci-dessous décrit les conditions applicables lors de la dernière vérification de cette page.

Ceci décrit les licences concernées et ne constitue pas un conseil juridique. Si la réponse a une importance commerciale, lisez vous-même les licences et consultez votre propre avocat.

Travail d'origine
InstantHMR, Naturalpad and LAAS-CNRS
Licence du projet d'origine
CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint)
Source du projet d'origine
github.com/Naturalpad-studio/InstantHMR
Code de LibreYOLO
MIT
Poids
CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial), republiés sur huggingface.co/LibreYOLO
Interprétation
The licence depends on the checkpoint. The n, t, s and m weights are CC BY-NC 4.0: attribution is required and commercial use is not allowed, because part of their training images (SA-1B, AI Challenger) are non-commercial. LibreInstantHMRm-mesh-commercial was trained on Harmony4D and commercially licensed COCO images only and is Apache-2.0, which allows commercial and closed-source use if you keep the license text and notices. Every checkpoint was also trained on the SAM 3D Body dataset annotations, released by Meta under the SAM License, whose terms pass through with the weights, and they embed the MHR body constants (Apache-2.0). The upstream code is Apache-2.0 (Naturalpad-studio/InstantHMR at commit 5437400d4b25c1972821e51916fac34bd96acce6; LICENSE and NOTICE in libreyolo/models/instanthmr); the mesh decode was written clean-room so that no SAM-licensed sam-3d-body code is used, and the fine-tuning trainer is original LibreYOLO MIT code. Upstream publishes ONNX only (momolesang/InstantHMR, revision 07988f51c8c8908cfc7bb44fc18f645c9551b0bf); LibreYOLO converts them to PyTorch and mirrors them as LibreYOLO/LibreInstantHMR{n,t,s,m}-mesh and -m-mesh-commercial, not gated, and prints a notice before auto-download.

InstantHMR is by Naturalpad and LAAS-CNRS (Naturalpad-studio/InstantHMR). The code is Apache-2.0. The weights licence depends on the checkpoint:

  • n, t, s and m: CC BY-NC 4.0, non-commercial only, because part of their training images (SA-1B, AI Challenger) are non-commercial.
  • m-commercial: Apache-2.0, trained on Harmony4D and commercially licensed COCO images only.

Every checkpoint was also trained on the SAM 3D Body dataset annotations, released by Meta under the SAM License, whose terms pass through with the weights. The mesh decode was written clean-room, so no SAM-licensed sam-3d-body code is used. The checkpoints are mirrored as LibreYOLO/LibreInstantHMR{n,t,s,m}-mesh and LibreYOLO/LibreInstantHMRm-mesh-commercial, not gated.

Citation

@misc{adjel2026instanthmr,
  title        = {InstantHMR: Real-Time Human Mesh Recovery on Your Phone},
  author       = {Adjel, Mohamed and Chalabi, Kahina and Bonnet, Vincent},
  year         = {2026},
  howpublished = {HAL preprint hal-05854387},
  url          = {https://hal.science/hal-05854387},
  note         = {LAAS report no. 26486}
}

Copié depuis le bloc de citation des auteurs sur github.com/Naturalpad-studio/InstantHMR#citation.

Vérifié avec LibreYOLO v1.8.0. Les tableaux de support, les checkpoints et les chiffres de benchmark de cette page sont générés à partir de la bibliothèque publiée et des poids publiés, et non rédigés à la main.