Published in The Visual Computer, 2023
This paper is about monocular depth estimation using engineered camera Point Spread Function (PSF).
Recommended citation: Mel, Mazen, Muhammad Siddiqui, and Pietro Zanuttigh. "End-to-end learning for joint depth and image reconstruction from diffracted rotation." The Visual Computer (2023): 1-17. https://link.springer.com/article/10.1007/s00371-023-03147-8
Published in Proceedings of the 6th International Conference on Optical Characterization of Materials, 2022
This paper is about hyper-spectral imaging and material characterization using spectral signature of objects.
Recommended citation: Amann, Simon, et al. "Material Characterization using a Compact Computed Tomography Imaging Spectrometer with Super-resolution Capability." Proceedings of the 6th International Conference on Optical Characterization of Materials, OCM 2023. https://www.research.unipd.it/handle/11577/3477950
Published in The 33rd British Machine Vision Conference (BMVC), 2022
This paper is about hyper-spectral image reconstruction and spatial super-resolution from CTIS measurements.
Recommended citation: Mel, Mazen, Alexander Gatto, and Pietro Zanuttigh. "Joint Reconstruction and Super Resolution of Hyper-Spectral CTIS Images." BMVC. 2022. https://bmvc2022.mpi-inf.mpg.de/1063.pdf
Published in Optical Engineering (SPIE), 2022
This paper is a learning based apporach for hyper-spectral image reconstruction using CTIS measurements.
Recommended citation: Zimmermann, Markus, et al. "Deep learning-based hyperspectral image reconstruction from emulated and real computed tomography imaging spectrometer data." Optical Engineering 61.5 (2022): 053103-053103. https://www.spiedigitallibrary.org/journals/optical-engineering/volume-61/issue-5/053103/Deep-learning-based-hyperspectral-image-reconstruction-from-emulated-and-real/10.1117/1.OE.61.5.053103.pdf
Published in Technologies (MDPI), 2019
This paper is about novel approaches for incremental and multi-task learning for semantic image segmentation task.
Recommended citation: Mel, Mazen, Umberto Michieli, and Pietro Zanuttigh. "Incremental and multi-task learning strategies for coarse-to-fine semantic segmentation." Technologies 8.1 (2019): 1. https://www.mdpi.com/2227-7080/8/1/1