roym899/pose_and_shape_evaluation
Toolbox to evaluate categorical pose and shape estimation methods
This toolbox helps researchers and engineers assess how well their algorithms can identify an object's 3D orientation (pose) and overall shape, especially when working with distinct categories of objects. It takes in the outputs from your object pose and shape estimation methods and provides standardized metrics to evaluate their accuracy and performance. Robotics researchers, computer vision scientists, and anyone developing perception systems for object manipulation or scene understanding would find this useful.
No commits in the last 6 months.
Use this if you are developing or comparing methods that estimate the 3D pose and shape of categorized objects (e.g., 'cup', 'chair') from sensor data, and you need a standardized way to measure their accuracy.
Not ideal if you are working with unstructured point clouds or general 3D reconstruction without a focus on predefined object categories and their specific pose/shape.
Stars
29
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/roym899/pose_and_shape_evaluation"
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.