0575077 20240402214344.920230901235959.9 978-1-7281-6328-4 10.1109/ICASSP49357.2023.10095386 Rhodes Island, Greece IEEE 2023 5 s. E cav_un_epca*0575081978-1-7281-6327-7PiscatawayIEEE2023 Light-sheet fluorescence microscopy Dual-view imaging deep learning image deconvolution cav_un_auth*0379363 Kerepecký Tomáš UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0261977 Liu J. US cav_un_auth*0453851 Ng X. W. US cav_un_auth*0453852 Piston D. W. US cav_un_auth*0453853 Kamilov U. S. US http://library.utia.cas.cz/separaty/2023/ZOI/kerepecky-0575077.pdf GA21-03921S GA ČR cav_un_auth*0412209 Three-dimensional fluorescence microscopy often suffers from anisotropy, where the resolution along the axial direction is lower than that within the lateral imaging plane. We address this issue by presenting Dual-Cycle, a new framework for joint deconvolution and fusion of dual-view fluorescence images. Inspired by the recent Neuroclear method, Dual-Cycle is designed as a cycle-consistent generative network trained in a self-supervised fashion by combining a dual-view generator and prior-guided degradation model. We validate Dual-Cycle on both synthetic and real data showing its state-of-the-art performance without any external training data. cav_un_auth*0453251 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023 /48./ 20230604 20230610 Rhodes GR IN 10000 10200 10201 2024 PR RVO:67985556 https://hdl.handle.net/11104/0344936 1 cav_un_auth*0355988 Washington University in St. Louis US cav_un_auth*0332359 Washington University School of Medicine US S 2023 C 2023 Rhodes Island, Greece IEEE 978-1-7281-6328-4 SCOPUS PUBMED WOS cav_un_epca*0575081 Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) IEEE 2023 Piscataway 978-1-7281-6327-7