Skip to content

This is the course project for 6.s890 Machine Learning For Inverse Graphics, where we did multi-object pose estimation.

License

Notifications You must be signed in to change notification settings

RuihanZhang2015/6s890-Machine-Learning-For-Inverse-Graphics-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

6.S980 multi view object pose refinement

This project aims to refine 3D object poses by performing gradient descent to minimize the loss between the actual image and the rendered images. We also performed bundle adjustment in the pose refinement by taking the images rendered from multiple cameras into consideration.

The figure_*.py files and src/* were created by us to compare the performence under different combinatons of loss functions and gradient descent hyperparameters.

About

This is the course project for 6.s890 Machine Learning For Inverse Graphics, where we did multi-object pose estimation.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published