Research
My research interests are the following areas of signal processing and computer vision:
- - image and video compression algorithms and standards
- - neural networks for image processing and computer vision
- - biomedical image processing
- - multimedia communications (coding, robust transmission, and encryption)
My research attitude is highly interdisciplinary, enabling me to tackle cross-layer activities involving signal processing, digital communications, networking, machine learning, and AI.
From September 2001 to June 2002 he was a visiting researcher at the Information Coding Lab, University of California, San Diego, directed by Prof. Pamela Cosman. Since 2002 he joined the Italian national body to the ISO, where he is involved in the standardization of JPEG 2000 - Part 11 (JPWL), devoted to the wireless applications of JPEG2000. Currently, he is following the standardization activities of the Moving Picture Experts Group (MPEG) in area of 3D video coding.
You can find more information, active projects and software at EIDOSLAB .
Recent preprints
- Tartaglione, Enzo, Carlo Alberto Barbano, and Marco Grangetto. "EnD: Entangling and Disentangling deep representations for bias correction." arXiv preprint arXiv:2103.02023 (to appear in IEEE CVPR 2021).
- E. Tartaglione, A. Bragagnolo, F. Odierna, A. Fiandrotti and M. Grangetto, "SeReNe: Sensitivity-Based Regularization of Neurons for Structured Sparsity in Neural Networks," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021.3084527, 2021.
- D. Cavagnino, M. Lucenteforte, M.Grangetto "High capacity reversible data hiding and content protection for radiographic images" to appear in Elsevier SignalProcessing.
- M. Farid, M. Lucenteforte, M.Grangetto "Panorama view with spatio-temporal occlusion compensation for 3D video coding" to appear in IEEE Trans. on Image Processing.
- R. Gaeta, M.Grangetto "DIP: Distributed identification of polluters in P2P live streaming" to appear in, ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS
- A. Fiandrotti, V. Bioglio, M. Grangetto, R. Gaeta, E. Magli "Band Codes for Energy-Efficient Network Coding with Application to P2P Mobile Streaming" to appear in IEEE TRANSACTIONS ON MULTIMEDIA
- V. Bioglio, R. Gaeta, M. Grangetto, M. Sereno "Rateless Codes and Random Walks for P2P Resource Discovery in Grids" to appear in IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
- R. Gaeta, M.Grangetto "Identification of Malicious Nodes in Peer-to-Peer streaming: A Belief Propagation Based Technique" to appear in, IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS "A novel interpolation method for 3D view synthesis" to be presented, 3DTV-CON 2012
Recent Projects
- [2012-2014] AMALFI, Advanced Methodologies for the Analysis and management of the Future Internet : joint collaboration between the Computer Science and Mathematical Departments of the University of Torino
- [2010-2012] COAST- COntent Aware Search retrieval and sTreaming ( ICT-248036) ICT project co-funded under EU's seventh framework (FP7) . Marco Grangetto is involved in the research activities on P2P video streaming.
- [2008-2009] SEAmless content delivery (ICT-214063) ICT project co-funded under EU's seventh framework (FP7) . Marco Grangetto is involved in the research activities on Multiple Description Video Coding, and P2P video streaming.
Research software download
The software available in this page is distributed "as is" for the only purpose of scientific dissemination and reproducibility of the research results.P2P stuff
- TurinStream (video streaming software)
- Rateless codes for file sharing
- Rateless codes for video streaming
- Compressive sensing for P2P
3D video
- Software for results in paper V. Paradiso, M. Lucenteforte, M.Grangetto, "A novel interpolation method for 3D view synthesis" presented at 3DTV-CON 2012 . The software has been obtained modifying the MPEG View Synthesis Reference Software (VSRS) available here). For test conditions and raw video data please refer to the 3DTV CfP.