Diego Valsesia received the Master of Science degree in Telecommunications Engineering from the Politecnico di Torino, Turin, Italy, in 2012, the Master of Science degree in Electrical and Computer Engineering from the University of Illinois at Chicago, Chicago, IL, USA, in 2013, and the Ph.D. degree in Electronic and Communication Engineering from the Politecnico di Torino in 2016. He is currently an Assistant Professor at the Department of Electronics and Telecommunications of Politecnico di Torino. His main research activities include compression of remote sensing images, and deep learning models for inverse problems in imaging. He worked on state-of-the-art models for image denoising, super-resolution, SAR despeckling, generative adversarial networks for point clouds as well as graph neural networks. He is a member of the ELLIS Society for the advancement of artificial intelligence in Europe, co-founder of the Torino ELLIS Research Unit, and a member of EURASIP Technical Area Commitee on Signal and Data Analytics for Machine Learning. Since 2021, he is an Associate Editor for the IEEE Transactions on Image Processing.
- First Place – European Space Agency AI4EO challenge on “Super-resolved image segmentation for Enhanced Sentinel 2 Agriculture“, 2021 (https://platform.ai4eo.eu/enhanced-sentinel2-agriculture)
- First Place – European Space Agency “Proba-V Super-Resolution” challenge, 2019 (Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro, Enrico Magli “DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images“)
- Best Paper Award – IEEE International Conference on Image Processing (ICIP), 2019, Diego Valsesia, Giulia Fracastoro, Enrico Magli “Image Denoising with Graph-convolutional Neural Networks“
- Best Paper Award – IEEE MultiMedia, 2019, Diego Valsesia, Giulio Coluccia, Tiziano Bianchi, Enrico Magli “ToothPic: Camera-Based Image Retrieval on Large Scales“, IEEE MultiMedia, vol. 26, no. 2, 2019, pp. 33-43
- Best Paper Award – ESA/CNES Onboard Payload Data Compression workshop (OBPDC) 2016, Diego Valsesia, Enrico Magli, Raffaele Vitulli “Near-lossless and lossy extension of the CCSDS-123 recommedation featuring rate and quality control“
- Top 10% paper award – IEEE International Workshop on Multimedia Signal Processing (MMSP),
2013, Diego Valsesia, Enrico Magli “Spatially Scalable Compressed Image Sensing with Hybrid Transform and Inter-Layer Prediction Model“
- Associate Editor – IEEE Transactions on Image Processing, 2021-2024
- Elected member – EURASIP Technical Area Committee (TAC) “SIG-DML: Signal and Data Analytics for Machine Learning”, 2021-2023
- Member – ELLIS Society (ellis.eu) and Founding Member – Torino ELLIS Research Unit
- Reviewer and TPC member for numerous international conferences (ICIP, EUSIPCO, CVPR, NeurIPS, ICLR, ICCV) and regular reviewer for several journals (IEEE TIP, IEEE TMM, IEEE TSP, IEEE TGRS, IEEE JTARS, IEEE SPL, IEEE GRSL)
- Guest Editor special issue on “Onboard Payload Data Compression and Processing for Spaceborne Imaging”, Taylor & Francis International Journal of Remote Sensing, 2016
Roles in funded projects
- Task leader – H2020 “Super-resolved compressive instrument in the visible and medium infrared for Earth observation applications (SURPRISE)”. Responsibility for the development of image reconstruction algorithms from the measurements acquired by the instrument according to compressive sensing techniques.
- Workpackage leader – Agenzia Spaziale Italiana “Spettrometro a Immagine a Super-risoluzione Spaziale nel medio Infrarosso (SISSI)”. Responsibility for the development of acquisition system model and image reconstruction algorithms from the measurements acquired by the instrument according to compressive sensing techniques.
- Workpackage leader – ESA ITI “Deep Learning in Space: Solar Flares Detection (DL-SPACE)”. Responsibility for the development of the machine learning technique for detection of flares from solar corona images.
- Deputy Manager – ESA NAVISP “Machine-Learning to model GNSS systems“. Responsibility for the study of machine learning methodologies to improve GNSS systems.