NeLy-EPFL/DeepFly3D

Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.

53
/ 100
Established

This project helps neuroscientists and biologists precisely track the 3D movements of tethered fruit flies (Drosophila) during experiments. You provide multi-view video recordings or image sequences of the fly, and it outputs accurate 3D pose estimates, identifying key body points. It's designed for researchers studying insect locomotion, behavior, or neural control in a lab setting.

Use this if you need to analyze the detailed 3D kinematics of tethered Drosophila from multi-camera video footage, without needing physical markers on the fly.

Not ideal if you need to track free-flying insects or other animal species, or if your experimental setup does not involve multiple synchronized camera views.

neuroscience Drosophila research animal behavior biomechanics motion analysis
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

96

Forks

17

Language

Jupyter Notebook

License

LGPL-3.0

Last pushed

Mar 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NeLy-EPFL/DeepFly3D"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.