CONF Shajkofci_ICIP2018_2018/IDIAP Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation by Use of Convolutional Neural Networks Shajkofci, Adrian Liebling, Michael blind deconvolution Convolutional Neural Networks microscopy point spread function EXTERNAL https://publications.idiap.ch/attachments/papers/2018/Shajkofci_ICIP2018_2018.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Shajkofci_Idiap-RR-07-2018 Related documents 2018 25th IEEE International Conference on Image Processing (ICIP) 2018 IEEE 3818-3822 2381-8549 978-1-4799-7061-2 10.1109/ICIP.2018.8451736 doi We present a semi-blind, spatially-variant deconvolution technique aimed at optical microscopy that combines a local estimation step of the point spread function (PSF) and deconvolution using a spatially variant, regularized Richardson-Lucy algorithm. To find the local PSF map in a computationally tractable way, we train a convolutional neural network to perform regression of an optical parametric model on synthetically blurred image patches. We deconvolved both synthetic and experimentally-acquired data, and achieved an improvement of image SNR of 1.00 dB on average, compared to other deconvolution algorithms. REPORT Shajkofci_Idiap-RR-07-2018/IDIAP Semi-blind spatially-variant deconvolution in optical microscopy with local Point Spread Function estimation by use of Convolutional Neural Networks Shajkofci, Adrian Liebling, Michael EXTERNAL https://publications.idiap.ch/attachments/reports/2018/Shajkofci_Idiap-RR-07-2018.pdf PUBLIC Idiap-RR-07-2018 2018 Idiap June 2018 Accepted to IEEE ICIP 2018 We present a semi-blind, spatially-variant deconvolution technique aimed at optical microscopy that combines a local estimation step of the point spread function (PSF) and deconvolution using a spatially variant, regularized Richardson-Lucy algorithm. To find the local PSF map in a computationally tractable way, we train a convolutional neural network to perform regression of an optical parametric model on synthetically blurred image patches. We deconvolved both synthetic and experimentally-acquired data, and achieved an improvement of image SNR of 1.00 dB on average, compared to other deconvolution algorithms.