Light Field Blind Motion Deblurring

Pratul P. Srinivasan, Ren Ng, Ravi Ramamoorthi

In Computer Vision and Pattern Recognition (CVPR), 2017 (Oral Presentation)

Paper, Video, Animated Results, Data and Results from Paper

Light Field Blurred with 3D Camera Motion

Our Light Field Blind Motion Deblurring Result

Contents

This repository contains:

1. Light_Field_Blind_Motion_Deblurring.ipynb Jupyter notebook with an implementation of our light field blind deblurring algorithm.

Data and Results File contains:

1. Data folder with mat files containing light fields used in our paper.
2. Results folder with mat files containing results from our paper.
3. parameters_to_use.txt Text file with suggested algorithm parameters to use for these examples.

Dependencies

This code depends on a working installation of Tensorflow and basic Python libraries (numpy, scipy, matplotlib).

Acknowledgments

This work was supported in part by ONR grant N00014152013, NSF grant 1617234, NSF graduate research fellowship DGE 1106400, a Google Research Award, the UC San Diego Center for Visual Computing, and a GPU donation from NVIDIA.