Open-source demo uses ViTPose+ Large to grade full-range pull-ups
spillai · x · 2026-10-30
Developer Jeremy Park built a computer vision demo that detects full range of motion in pull-ups using ViTPose+ Large for pose estimation via the vlmrun Gateway. It combines vertical head displacement with elbow angles: reps with insufficient height or bent-arm starts don't count, while dead-hang-to-over-the-bar reps do.
Thresholds can be calibrated per person since pull-up form varies. The code is open-source on GitHub (jeremyipark/vision-demos, 914 stars), which also includes demos for chin-ups, push-ups, deadlifts, running, rock climbing, and dance synchronization.
More from coding & agent
- Agent engineering feels like Elon running the factory: hunting bottlenecks and nudging agents at 3am — robleclerc · 2026-10-30
- btrfs zstd compression cuts 35GB of daily agent JSON output to ~1/20 the disk space — mgostIH · 2026-10-30
- Building a Black Friday deal-hunting agent: agentic commerce starts with discounts — jeff_weinstein · 2026-10-30
- Sentry CEO on agent determinism: why system prompts are almost never the answer — zeeg · 2026-10-30
- Claude Opus autonomously builds a walkable 3D IKEA room from product photos via HF agents — victormustar · 2026-10-30
- claude-obsidian hits 16k stars: Claude Code auto-builds and maintains a linked Markdown knowledge vault — JeremyCMorgan · 2026-10-30