YangHai-1218/SCFlow
Shape-Constraint Recurrent Flow for 6D Object Pose Estimation (CVPR 2023)
This project helps improve the precision of identifying the 3D position and orientation (pose) of objects from images. It takes an input image of an object and its initial estimated 6D pose, then refines that estimate using the object's known 3D shape. The output is a more accurate 6D pose, which is crucial for applications like robotic grasping or augmented reality. This tool is designed for computer vision engineers and researchers working on real-time object manipulation and scene understanding.
No commits in the last 6 months.
Use this if you need to precisely determine an object's 6D pose from 2D images, especially when high accuracy is critical for downstream tasks.
Not ideal if your application does not require extremely precise 6D pose estimation or if you do not have detailed 3D models of the target objects.
Stars
67
Forks
8
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YangHai-1218/SCFlow"
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.