dual-pixel-defocus-disparity's Introduction

Official respository for "Modeling Defocus-Disparity in Dual-Pixel Sensors", ICCP 2020

BibTeX

@INPROCEEDINGS{punnappurath2020modeling,
   author={Abhijith Punnappurath and Abdullah Abuolaim and Mahmoud Afifi and Michael S. Brown},
   booktitle={IEEE International Conference on Computational Photography (ICCP)}, 
   title={Modeling Defocus-Disparity in Dual-Pixel Sensors}, 
   year={2020}
}

How to run

This is the code for the optimization-based approach described in Section 4.1 of our paper. The implementation is in Matlab.
The post-process edge-aware filtering described in Section 4.3 consists of a bilateral solver and a guided filter. Official implementations released by the authors have been used - the bilateral solver is in Python and the guided filter in Matlab.
To obtain our final result, run Steps 1, 2, and 3 sequentially, where Step 1 is the main optimization, and Steps 2 and 3 are the post-process bilateral solver and guided filter, respectively.
The data corresponding to Fig. 7 of our paper can be found here, and Figs. 1 and 8 can be found here.
Running the code as is produces our result in Fig. 8(f) third column.
Other outputs can be generated by appropriately setting the input image path here in Step 1, and here and here in Steps 2 and 3, respectively.
- The img_name variable to use for Steps 2 and 3 will be displayed when Step 1 finishes execution.
Note that the optimization-based approach is very slow since it requires minimizing our cost function of equation (7) at each window.

Also check out

If you are here out of interest in dual-pixel depth estimation in general, also check out my implementation of the stereo-based algorithm used on the Google Pixel 2.

Recommend Projects