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.
- Tareas
- body mesh
- Instalación
pip install libreyolo- Nivel de compatibilidad
- Compatible, desde v1.8.0. Modelos entrenables de apoyo: se mantienen operativos en CI y reciben funciones cuando surge la oportunidad.
- Proyecto original
- InstantHMR de Naturalpad and LAAS-CNRS, CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint). Artículo, fuente
- Licencias
- Código Apache-2.0, pesos CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial). Uso comercial
Install
InstantHMR needs no optional extra. The default person detector,
LibreRFDETRm.pt, needs the RF-DETR extra.
pip install "libreyolo[rfdetr]"Predict
Weights download from the LibreYOLO Hugging Face mirrors on first use, after a licence notice.
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) pixelsfrom 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.
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
| Tarea | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Body mesh | Body mesh to ONNX: compatible | Body mesh to TorchScript: no compatible | Body mesh to ExecuTorch: no compatible | Body mesh to TensorRT: no compatible | Body mesh to OpenVINO: no compatible | Body mesh to Paddle: no compatible | Body mesh to MNN: no compatible | Body mesh to RKNN: no compatible | Body mesh to Axelera: no compatible | Body mesh to ncnn: no compatible | Body mesh to TFLite: no compatible | Body mesh to CoreML: no compatible | Body mesh to Core AI: no compatible |
export(format="onnx") writes a graph with image and cliff_cond inputs
and the mesh faces in its metadata.
from libreyolo import LibreYOLO model = LibreYOLO("LibreInstantHMRm-mesh.pt")model.export(format="onnx") # inputs image, cliff_cond; faces in metadataCheckpoints
| Archivo | Licencia de los pesos |
|---|---|
| Body mesh | |
| LibreInstantHMRn-mesh.pt | cc-by-nc-4.0 |
| LibreInstantHMRt-mesh.pt | cc-by-nc-4.0 |
| LibreInstantHMRs-mesh.pt | cc-by-nc-4.0 |
| LibreInstantHMRm-mesh.pt | cc-by-nc-4.0 |
| LibreInstantHMRm-mesh-commercial.pt | apache-2.0 |
Todos los archivos anteriores existen hoy en la organización de LibreYOLO y se descargan la primera vez que se usan.
Licensing
Comprueba la licencia en el repositorio de Hugging Face de los pesos concretos que descargues. Cada checkpoint de la organización de LibreYOLO incluye una, y no siempre es la misma en toda una familia. Ese repositorio es la fuente autorizada; el resumen siguiente describe qué se aplicaba cuando se verificó esta página por última vez.
Esta es una descripción de las licencias implicadas, no asesoramiento legal. Si la respuesta es importante a nivel comercial, lee las licencias y busca tu propio asesoramiento.
- Trabajo original
- InstantHMR, Naturalpad and LAAS-CNRS
- Licencia del proyecto original
- CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint)
- Fuente del proyecto original
- github.com/Naturalpad-studio/InstantHMR
- Código de LibreYOLO
- MIT
- Pesos
- CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial), republicados en huggingface.co/LibreYOLO
- Interpretación
- 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,sandm: 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}
}Copiado del bloque de cita de los autores en github.com/Naturalpad-studio/InstantHMR#citation.