Skip to content

Fully Connected Residual Network (FCRN) for single view depth prediction

Notifications You must be signed in to change notification settings

kedarvilankar/FCRN-Keras-Implementation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fully Connected Residual Network (FCRN) for single view depth prediction

'FCRN.py' is the implementation of Laina et. al. 2016 deep netwrok to predict depth in single view images.

'runFCRNonNYU2_test.py' and 'runFCRNonSYNS_test.py' is the code to geenrate depth maps on the test sets of NYU2 and SYNS dataset using a pretrained model.

Reference

Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016). Deeper depth prediction with fully convolutional residual networks. In 2016 Fourth International Conference on 3D Vision (3DV) (pp. 239–248).

About

Fully Connected Residual Network (FCRN) for single view depth prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages