Phone (office): +39 049 827 7774
Biography
Mazen Mel is a PhD student in the Department of Information Engineering at the University of Padova. He received a First Cycle degree in Physics and Technology in 2016 and an Engineering degree in Telecommunications in 2019 from The Higher School of Communications of Tunis (Sup’Com) in Tunisia and a master’s degree in ICT in 2021 from the University of Padova. His research activities are about computational imaging/photography and computer vision, in particular hyper-spectral imaging, depth of field extention (EDoF), and monocular depth estimation. He works in collaboration with Sony Europe B.V. Stuttgart technology center.
Research areas
Quantitative Phase Imaging
Cell imaging using holographic microscopes.
Snapshot Spectral Sensing
Different from scanning-based imaging spectrometers, snapshot systems offer greater flexibility and can capture full spectrum of still as well as dynamic scenes in a single coded 2D measurement achieved by multiplexing spatial and spectral information using a com- bination of lenses, dispersive elements, and coded aperture masks.
Monocular Depth Estimation
Currently working on physics-aware depth estimation solutions that rely on depth-dependent optical aberrations introduced by the imaging system as reliable depth cues.
Publications
2024
HoloADMM: High-Quality Holographic Complex Field Recovery Proceedings Article
In: Proceedings of European Conference on Computer Vision (ECCV), 2024.
Joint Reconstruction and Spatial Super-resolution of Hyper-Spectral CTIS Images via Multi-Scale Refinement Journal Article
In: IEEE Transactions on Computational Imaging, 2024.
APPARATUSES AND METHODS FOR COMPUTER TOMOGRAPHY IMAGING SPECTROMETRY Patent
2024.
2023
CAMERA, METHOD AND IMAGE PROCESSING METHOD Patent
2023.
Material Characterization using a Compact Computed Tomography Imaging Spectrometer with Super-resolution Capability Proceedings Article
In: Proceedings of the 6th International Conference on Optical Characterization of Materials, OCM 2023, pp. 139–148, 2023.
2022
End-to-end learning for joint depth and image reconstruction from diffracted rotation Journal Article
In: arXiv preprint arXiv:2204.07076, 2022.
Deep learning-based hyperspectral image reconstruction from emulated and real computed tomography imaging spectrometer data Journal Article
In: Optical Engineering, vol. 61, no. 5, pp. 053103–053103, 2022.
Joint Reconstruction and Super Resolution of Hyper-Spectral CTIS Images Conference
BMVC, 2022.
2019
Incremental and multi-task learning strategies for coarse-to-fine semantic segmentation Journal Article
In: Technologies, vol. 8, no. 1, pp. 1, 2019.