Project-Splinter/MonoPort
Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)
This project helps capture a full 3D digital model of a moving, clothed person in real-time using just a single standard webcam. You feed a live video stream (or pre-recorded video/images) of a person into the system, and it outputs a complete 3D volumetric model, including their back. This tool is ideal for creators in virtual reality, augmented reality, or anyone needing to rapidly create 3D digital avatars from video.
576 stars. No commits in the last 6 months.
Use this if you need to quickly generate a realistic 3D model of a person's performance or movements for virtual environments, telepresence, or digital content creation.
Not ideal if you require extremely high-fidelity, production-ready 3D scans for film or complex animation, or if you don't have access to powerful graphics processing units.
Stars
576
Forks
83
Language
Python
License
—
Category
Last pushed
Jun 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Project-Splinter/MonoPort"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.