# FAH paper distills Meta's SAM 3D Body into real-time hand models as Meta's open vision models reach labs and wheelchairs

The arXiv paper fits MANO or MHR-Hand meshes and estimates contact without object geometry. Separately, a Pittsburgh wheelchair-arm project and a Berkeley Lab beamline pipeline run Meta's DINO and SAM models on their own hardware.

- Published: 2026-11-07T06:25:02.319Z
- Canonical: https://polylog.news/ai/2026-11-07/fah-paper-distills-meta-s-sam-3d-body-into-real-time-hand-mo
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2611.07711), [Meta AI (University of Pittsburgh)](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/), [Meta AI (Genesis Mission)](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/)

A new paper, "Fast and Accurate Hand Estimation in Pixels, Interaction and World Space" by Jinkun Cao, posted November 5, introduces FAH. FAH is a family of models built on the hand branch of Meta's SAM 3D Body and adapted through fine-tuni…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-07/fah-paper-distills-meta-s-sam-3d-body-into-real-time-hand-mo (subscription information: https://polylog.news/pricing).