Skip to content

3D reconstruction and Plane detection using plane-to-plane homography constraints for uncalibrated image pair under Manhattan World Assumption.

License

Notifications You must be signed in to change notification settings

ziliHarvey/Homographies-for-Plane-Detection-and-3D-Reconstruction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

3D-Reconstruction-using-Homography-Constraints-for-Uncalibrated-Images

This repo contains an implementation of 3D reconstruction and Plane detection using plane-to-plane homography constraints for uncalibrated image pair under Manhattan World Assumption. Given 2 images of the same scene from different perspective which has three main orthogonal planes in space, the planes can be reconstructed up to scale. Notice here we don't require any calibration parameters, everything is computed from 2 raw images from scratch!

Sample Results

Pipeline

Run

MATLAB 2018 or higher version is recommended.

3D Reconstruction and Plane Detection

Run reconstructionUsingHomography.m

(Optional) Vanishing Point Detection

Run vanishingPointDetection.m

About

3D reconstruction and Plane detection using plane-to-plane homography constraints for uncalibrated image pair under Manhattan World Assumption.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages