Abstract
The synchronization problem has attracted a lot of attention in the community thanks to its application in a variety of Computer Vision tasks. The goal of ‘’synchronization’’ is to infer the unknown states of a network of nodes, where only the ratio (or difference) between pairs of states can be measured. Typically, states are represented by elements of a group, such as the Symmetric Group or the Special Euclidean Group. The former can for example represent local labels of a set of features, as it occurs in multi-view matching applications. The latter can for example represent camera reference frames (e.g., in the context of structure from motion or pose graph optimization), or local coordinates of 3D points when dealing with 3D registration. Other applications include image mosaicking (where states are represented as homographies) and motion segmentation (where states are represented as binary matrices).
The synchronization problem can be modeled as a graph where nodes correspond to the unknown states and edges encode the pairwise measures, and it is well-posed only if such a graph is connected. Solving a synchronization problem is equivalent to imposing cycle consistency, that is the property that the composition of relative measures along any cycle in the graph gives the identity. Cycle consistency has also been employed by recent techniques that jointly optimize neural networks across multiple domains. In practice measures are corrupted by errors, thus the task is to address synchronization in a way that such errors are globally compensated.
Short Bio
Federica Arrigoni received her MS degree in Mathematics from the University of Milan (Italy) in 2013, and the PhD degree in Industrial and Information Engineering from the University of Udine (Italy) in 2018. Her PhD thesis titled “Synchronization Problems in Computer Vision” was awarded from the Italian Association for Computer Vision, Pattern Recognition and Machine Learning (CVPL) in 2018 and from the University of Udine in 2019. From 2018 to 2020 she was a postdoctoral researcher with the Czech Institute of Informatics, Robotics, and Cybernetics (CIIRC) of the Czech Technical University in Prague. She is currently an assistant professor with the Department of Information Engineering and Computer Science of the University of Trento (Italy). She co-organized a tutorial on “Synchronization and cycle consistency in Computer Vision” at CVPR20, and she regularly serves as reviewer for CVPR, ECCV, ICCV and 3DV. Her current research focuses on geometric problems in computer vision, including structure from motion, 3D registration, multi-image matching and motion segmentation.
Eleonora Maset received the M.Sc. degree in Environmental Engineering and the Ph.D. degree in Industrial and Information Engineering from the University of Udine, Italy, in 2015 and 2019, respectively. In 2019 she was a post-doc researcher at the University of Udine; in this period she collaborated with Helica srl to the development of LiDAR point cloud classification methods. She currently collaborates with the Polytechnic Department of Engineering and Architecture (DPIA), University of Udine. She received the Young Author’s Award at the XXIV ISPRS Congress for the work “Bundle Block Adjustment with Constrained Relative Orientations”. She served as reviewer for CVPR, ECCV, ICCV and 3DV. Her research interests include image orientation, point cloud processing and indoor modelling.
Florian Bernard is a Visiting Professor at the chair of Computer Vision & Artificial Intelligence at the Technical University of Munich. Before that, he held a position as postdoctoral researcher in the Graphics, Vision and Video group at the Max-Planck-Institute for Informatics, as well as at the University of Luxembourg. In 2016 he received the Ph.D. degree for his work on multi-shape analysis from the University of Luxembourg, which was awarded with the BVM-award. His research interests are computer vision, pattern recognition and machine learning, with a focus on integrating computational models derived from human knowledge into learning systems, as well as optimisation methods relevant for data canonicalisation. He served as area chair for WACV, regularly reviews for TPAMI, JMLR, IJCV, TOG, CVPR, ICCV, ECCV, AAAI, ACCV, and 3DV, and received a CVPR 2019 Outstanding Reviewer award.
Andrea Fusiello received his Laurea (Master) degree in Computer Science from the University of Udine in 1994 and the Dottorato di Ricerca (PhD) in Computer Engineering from the University of Trieste in 1999. After graduating, he has been EPSRC Visiting Research Fellow at Heriot-Watt University, Edinburgh in 1999 (for 6 months). From 2000 to 2011 he was with the Department of Computer Science, University of Verona, where he taught Computer Graphics and Computer Vision, as Ricercatore (Assistant Professor) first and Associate Professor since 2005. In 2012 he moved to the University of Udine, at the Department of Management, Electrical, and Mechanical Engineering, where he teaches Fundamentals of Computer Science (undergraduate) and Computer Vision (graduate). In 2013 he has been awarded the national scientific qualification as Full Professor. Andrea Fusiello was Associate Editor of “Pattern Recognition” and “IET Computer Vision” for three years each, and he regularly serves as reviewer for CVPR, ICCV, and ECCV. He was the workshop chair at ECCV12 and ECCV20 and general chair of 3DV18. In 2016 he has been appointed as co-chair of WG II/1 of the ISPRS. His research focuses on various topics in Computer Vision, Photogrammetry and Image Analysis: stereo matching, epipolar rectification, tracking, motion segmentation, mosaics, view synthesis, auto-calibration, 3-D modelling, model acquisition. Andrea Fusiello has published more than 160 papers, of which 39 in international journals.