TY - UNPB
T1 - Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space
AU - Mazilu, Ioana
AU - Wang, Shunxin
AU - Dummer, Sven
AU - Veldhuis, Raymond
AU - Brune, Christoph
AU - Strisciuglio, Nicola
N1 - Accepted at CAIP2023
PY - 2023/7/28
Y1 - 2023/7/28
N2 - Though modern microscopes have an autofocusing system to ensure optimal focus, out-of-focus images can still occur when cells within the medium are not all in the same focal plane, affecting the image quality for medical diagnosis and analysis of diseases. We propose a method that can deblur images as well as synthesize defocus blur. We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations among the representations of different blur levels in the latent space. This allows for the exploration of different blur levels of an object by linearly interpolating/extrapolating the latent representations of images taken at different focal planes. Compared to existing works, we use a simple architecture to synthesize images with flexible blur levels, leveraging the linear latent space. Our regularized autoencoders can effectively mimic blur and deblur, increasing data variety as a data augmentation technique and improving the quality of microscopic images, which would be beneficial for further processing and analysis.
AB - Though modern microscopes have an autofocusing system to ensure optimal focus, out-of-focus images can still occur when cells within the medium are not all in the same focal plane, affecting the image quality for medical diagnosis and analysis of diseases. We propose a method that can deblur images as well as synthesize defocus blur. We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations among the representations of different blur levels in the latent space. This allows for the exploration of different blur levels of an object by linearly interpolating/extrapolating the latent representations of images taken at different focal planes. Compared to existing works, we use a simple architecture to synthesize images with flexible blur levels, leveraging the linear latent space. Our regularized autoencoders can effectively mimic blur and deblur, increasing data variety as a data augmentation technique and improving the quality of microscopic images, which would be beneficial for further processing and analysis.
KW - Microscope images
KW - Deblurring
KW - Defocus blur synthesis
KW - Regularized autoencoders
U2 - 10.48550/arXiv.2307.15461
DO - 10.48550/arXiv.2307.15461
M3 - Preprint
BT - Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space
PB - ArXiv.org
ER -