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.
- Task
- body mesh
- Instalasi
pip install libreyolo- Tier dukungan
- Didukung, sejak v1.8.0. Model pendukung yang dapat dilatih: CI dijaga tetap lulus, fitur ditambahkan saat ada kesempatan.
- Proyek upstream
- InstantHMR oleh Naturalpad and LAAS-CNRS, CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint). Makalah, sumber
- Lisensi
- Kode Apache-2.0, bobot CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial). Penggunaan komersial
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
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Body mesh | Body mesh to ONNX: didukung | Body mesh to TorchScript: tidak didukung | Body mesh to ExecuTorch: tidak didukung | Body mesh to TensorRT: tidak didukung | Body mesh to OpenVINO: tidak didukung | Body mesh to Paddle: tidak didukung | Body mesh to MNN: tidak didukung | Body mesh to RKNN: tidak didukung | Body mesh to Axelera: tidak didukung | Body mesh to ncnn: tidak didukung | Body mesh to TFLite: tidak didukung | Body mesh to CoreML: tidak didukung | Body mesh to Core AI: tidak didukung |
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
| Berkas | Lisensi bobot |
|---|---|
| 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 |
Setiap berkas di atas saat ini tersedia di organisasi LibreYOLO dan diunduh saat pertama kali digunakan.
Licensing
Periksa lisensi di repositori Hugging Face untuk bobot tertentu yang diunduh. Setiap checkpoint di organisasi LibreYOLO memiliki lisensi, dan lisensinya tidak selalu sama dalam satu family. Repositori tersebut adalah sumber resmi. Ringkasan di bawah menjelaskan ketentuan yang berlaku saat halaman ini terakhir diverifikasi.
Ini adalah deskripsi lisensi yang terlibat, bukan nasihat hukum. Jika jawabannya penting secara komersial, baca sendiri lisensinya dan mintalah nasihat dari penasihat hukum Anda.
- Karya asli
- InstantHMR, Naturalpad and LAAS-CNRS
- Lisensi upstream
- CC-BY-NC-4.0 (n, t, s, m checkpoints); Apache-2.0 (m commercial checkpoint)
- Sumber upstream
- github.com/Naturalpad-studio/InstantHMR
- Kode LibreYOLO
- MIT
- Bobot
- CC-BY-NC-4.0 (n, t, s, m); Apache-2.0 (m-commercial), dipublikasikan ulang di huggingface.co/LibreYOLO
- Interpretasi
- 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}
}Disalin dari blok sitasi penulis di github.com/Naturalpad-studio/InstantHMR#citation.