Climbing analysis in 3D with iPhone LiDAR: open-source SAM 3.1 + ViTPose demos
dosco · x · 2026-09-25
Developer jeremyipark open-sourced vision-demos (357 stars on GitHub), featuring a rock climbing analyzer built with iPhone 15 Pro LiDAR depth data. Using SAM 3.1 for hold segmentation and ViTPose-plus-large for pose estimation, the 3D version supports videos where the camera follows the climber, reconstructs the wall, holds and climber in 3D, measures real-world distance traveled in meters, and visualizes which hand or foot activated each hold.
The repo also includes:
- running: cadence, foot-strike timing, and average knee shape at contact
- chinups: rep counting with ascent/descent timing
- dancesync: similarity metrics for dancers performing the same choreography
Each sub-project has its own README with setup instructions, Apache-2.0 licensed.
More from coding & agent
- Dhravya Shah Details How typesafeAI's Jev Improves AI Memory and Context Engineering — blaizedsouza · 2026-09-25
- AI compliance startup CompAI hits 1,000+ paying business customers in under a year — JosephJacks_ · 2026-09-25
- Sleep Data for Personal AI? Separating Daily Signals from Hard Rules — sujingshen · 2026-09-25
- Markdown Is the New Source Code: How to Manage Runbooks, Prompts and Rules for Agents — arpit_bhayani · 2026-09-25
- The personal agent supercycle needs hard authorization boundaries, not autonomy — sujingshen · 2026-09-25
- Mnemos.Field nears launch: a virtual world where humans and AI agents both register and participate — RileyRalmuto · 2026-09-25