qq456cvb/CPPF
CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR2022)
This project helps operations engineers and robotics developers accurately determine the 3D position and orientation (9D pose) of common objects in real-world environments using only images. It takes raw RGB-D images or bounding box masks as input and outputs precise pose estimates for various object categories like bottles, chairs, and laptops. This is ideal for those working with robotic manipulation or augmented reality applications.
Use this if you need robust, category-level 3D object pose estimation in 'wild' or unstructured environments without needing extensive real-world training data.
Not ideal if your application requires object detection or segmentation as a primary output, rather than just pose estimation for already identified objects.
Stars
56
Forks
9
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/qq456cvb/CPPF"
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.