Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur
This addresses domain gaps in deep learning models for defocus deblurring, particularly for smart glasses and other fixed-focus cameras, though it is incremental as it builds on existing synthesis approaches.
The paper tackles the problem of defocus blur in fixed-focus cameras by proposing an efficient dataset synthesis method that models depth-dependent defocus and spatially varying optical aberrations, resulting in a network trained on low-resolution synthetic images that generalizes effectively to high-resolution (12MP) real-world images.
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.