Metraipolis › archive › dc_e527675b262f
InstantHMR : Real-Time Human Mesh Recovery on Your Phone — arXiv:2611.09195
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09195
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:45:17.878Z
- SHA-256 of the archived text
a975263e3a99d13c2ae89cd9f295fba4812d6112c339f584d45dbe46de48bcfd- Stable URL of this page
https://metraipolis.com/documento/dc_e527675b262f
How to cite
InstantHMR : Real-Time Human Mesh Recovery on Your Phone — arXiv:2611.09195 — arXiv (en), https://arxiv.org/abs/2611.09195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e527675b262f (Metraipolis archive dc_e527675b262f, sha256 a975263e3a99d13c2ae89cd9f295fba4812d6112c339f584d45dbe46de48bcfd)
BibTeX
@misc{dce527675b262f,
title = {InstantHMR : Real-Time Human Mesh Recovery on Your Phone — arXiv:2611.09195},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09195},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e527675b262f; sha256 a975263e3a99d13c2ae89cd9f295fba4812d6112c339f584d45dbe46de48bcfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-time 3D human mesh recovery from a single image on mobile devices is a challenging problem with many applications, including robotics, biomechanics, AR/VR, and exergames. Current state-of-the-art models are either too slow to run efficiently on mobile devices or sacrifice accuracy for speed. We present InstantHMR, a family of open-source single-image regressors suited for mobile inference, based on the Momentum Human Rig (MHR) parametric model and trained exclusively on publicly available annotations from the SAM 3D Body dataset. Our approach achieves remarkable performance on a Samsung Galaxy S23 NPU, recovering a 6,890-vertex body mesh in 5.5 ms per person, and 0.98 ms on an NVIDIA RTX 4070 GPU. This speed surpasses all existing methods we evaluated. On mobile, it is 12x faster than the single mobile-compatible method that slightly outperforms ours in accuracy, while achieving competitive accuracy with 40.0 mm PA-MPJPE on 3DPW, 48.8 mm on EMDB and 41.7 mm on RICH. To ensure fair comparisons, we re-evaluate 11 state-of-the-art methods under a unified protocol aligned with the closest MHR-based competitors, including Meta's official MHR-to-SMPL conversion, and report their reproduction results. Additionally, we measure latency across eight different targets, ranging from desktop TensorRT to two phone NPUs. Code and models are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.09195 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:37:47.225Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).