RuojinCai/ExtremeRotation_code
Extreme Rotation Estimation using Dense Correlation Volumes
This tool helps researchers and computer vision engineers precisely determine the relative 3D rotation between two RGB images, even if they show completely different parts of a scene. You provide a pair of images, and it outputs the estimated 3D rotation, useful for tasks like scene reconstruction or robotic navigation where camera viewpoints might vary widely. It is designed for those working with large image datasets from diverse environments.
No commits in the last 6 months.
Use this if you need to accurately estimate the rotational relationship between two images that have little to no visual overlap, for example, two photos taken far apart in a large room or different streets in a city.
Not ideal if you primarily work with images that have significant overlap and require simpler, faster rotation estimation methods.
Stars
45
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/RuojinCai/ExtremeRotation_code"
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.