Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur

TL;DR

This paper introduces an efficient synthetic dataset generation method for defocus deblurring that models depth-dependent defocus and optical aberrations, enabling deep learning models to generalize well to real-world high-resolution images.

Contribution

The authors present a scalable, domain-agnostic dataset synthesis approach that captures complex optical effects without requiring real-world data fine-tuning.

Findings

Synthetic training data improves real-world high-res image deblurring.

Model trained on synthetic data generalizes across diverse scenes.

Method reduces reliance on high-quality RGB-D datasets.

Abstract

Modern cameras with large apertures often suffer from a shallow depth of field, resulting in blurry images of objects outside the focal plane. This limitation is particularly problematic for fixed-focus cameras, such as those used in smart glasses, where adding autofocus mechanisms is challenging due to form factor and power constraints. Due to unmatched optical aberrations and defocus properties unique to each camera system, deep learning models trained on existing open-source datasets often face domain gaps and do not perform well in real-world settings. In this paper, we propose an efficient and scalable dataset synthesis approach that does not rely on fine-tuning with real-world data. Our method simultaneously models depth-dependent defocus and spatially varying optical aberrations, addressing both computational complexity and the scarcity of high-quality RGB-D datasets. Experimental results demonstrate that a network trained on our low resolution synthetic images generalizes effectively to high resolution (12MP) real-world images across diverse scenes.