Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image

TL;DR

This paper introduces an unsupervised method that jointly estimates defocus maps and recovers all-in-focus images from a single dual-pixel image, leveraging optical modeling and optimization.

Contribution

It presents a novel joint optimization approach for defocus map estimation and deblurring from dual-pixel images, avoiding large labeled datasets and improving accuracy.

Findings

Outperforms prior methods in defocus map estimation

Achieves superior deblurring results

Operates effectively with a one-time calibration

Abstract

We present a method that takes as input a single dual-pixel image, and simultaneously estimates the image's defocus map -- the amount of defocus blur at each pixel -- and recovers an all-in-focus image. Our method is inspired from recent works that leverage the dual-pixel sensors available in many consumer cameras to assist with autofocus, and use them for recovery of defocus maps or all-in-focus images. These prior works have solved the two recovery problems independently of each other, and often require large labeled datasets for supervised training. By contrast, we show that it is beneficial to treat these two closely-connected problems simultaneously. To this end, we set up an optimization problem that, by carefully modeling the optics of dual-pixel images, jointly solves both problems. We use data captured with a consumer smartphone camera to demonstrate that, after a one-time calibration step, our approach improves upon prior works for both defocus map estimation and blur removal, despite being entirely unsupervised.