Shadowgraph
About
Sign in

jeremyipark/vision-demos

Fun real-world computer vision demos!

205

stars

4

commits

Python

primary language

Sep 10, 2026

updated

README

vision-demos

Real-world computer vision demos.

ProjectWhat it doesKey model
dance_syncCompares dancers' sync performing the same choreography and computes a similarity metric.vitpose-plus-large
chin_upsCounts chin-up reps from a clip and times the ascent and descent of each one.vitpose-plus-large
runningMeasures a runner's cadence, times every foot strike, and averages the knee shape at contact.vitpose-plus-large

Dancers with pose overlays on the left and a sync score panel on the right

A chin-up at the top of the rep with a pose overlay on the left and a rep-timing panel on the right

A runner on a treadmill with a pose overlay on the left and a live cadence panel on the right

Each project has its own README with setup and instructions.

License

Apache-2.0.

Contributors

jeremyipark

4 commits

See what people are saying

Hacker News (1)

Ask HN: What are you working on? (September 2026)

0 points · Sep 14, 2026

Similar repos

open-mmlab/mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

7,894

CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot…

34,444

UCSF-MSLAB/HomeVideoAnalysis

Generate spatiotemporal metrics from collected home videos.

1

ChaoYue0307/ropedia-academy

Ropedia Academy — interactive bilingual learning app for egocentric vision, 3D reconstruction,…

3

IntelligentSensingAndRehabilitation/PosePipeline

PosePipe is a human pose estimation (HPE) pipeline to facilitate home movement analysis from videos

97

ZeyuLing/monocular-motion-capture-leaderboard

Space

0

amanichopra/ai-yoga-trainer

0

cuevhv/mamma

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.

801

Languages

Python

100.0%

jeremyipark/vision-demos

Fun real-world computer vision demos!

205

stars

4

commits

Python

primary language

Sep 10, 2026

updated

README

vision-demos

Real-world computer vision demos.

ProjectWhat it doesKey model
dance_syncCompares dancers' sync performing the same choreography and computes a similarity metric.vitpose-plus-large
chin_upsCounts chin-up reps from a clip and times the ascent and descent of each one.vitpose-plus-large
runningMeasures a runner's cadence, times every foot strike, and averages the knee shape at contact.vitpose-plus-large

Dancers with pose overlays on the left and a sync score panel on the right

A chin-up at the top of the rep with a pose overlay on the left and a rep-timing panel on the right

A runner on a treadmill with a pose overlay on the left and a live cadence panel on the right

Each project has its own README with setup and instructions.

License

Apache-2.0.

See what people are saying

Hacker News (1)

Ask HN: What are you working on? (September 2026)

0 points · Sep 14, 2026

Similar repos

open-mmlab/mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

7,894

CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot…

34,444

UCSF-MSLAB/HomeVideoAnalysis

Generate spatiotemporal metrics from collected home videos.

1

ChaoYue0307/ropedia-academy

Ropedia Academy — interactive bilingual learning app for egocentric vision, 3D reconstruction,…

3

IntelligentSensingAndRehabilitation/PosePipeline

PosePipe is a human pose estimation (HPE) pipeline to facilitate home movement analysis from videos

97

ZeyuLing/monocular-motion-capture-leaderboard

Space

0

amanichopra/ai-yoga-trainer

0

cuevhv/mamma

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.

801

Contributors

jeremyipark

4 commits

Languages

Python

100.0%