Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image
This addresses image deblurring and depth estimation for photography applications, but is incremental as it builds on existing dual-pixel sensor techniques.
The paper tackles the problem of estimating defocus maps and recovering all-in-focus images from single dual-pixel images, showing that joint optimization improves performance over prior independent methods, with results demonstrated on consumer smartphone camera data.
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.