C
Curzio Basso
Researcher at University of Genoa
Publications - 27
Citations - 759
Curzio Basso is an academic researcher from University of Genoa. The author has contributed to research in topics: Sparse approximation & Segmentation. The author has an hindex of 10, co-authored 24 publications receiving 696 citations. Previous affiliations of Curzio Basso include University of Basel.
Papers
More filters
Journal ArticleDOI
Reanimating Faces in Images and Video
TL;DR: A method for photo‐realistic animation that can be applied to any face shown in a single image or a video, which allows for head rotations and speech in the original sequence, but neither of these motions is required.
Journal ArticleDOI
Dynamic contrast-enhanced magnetic resonance imaging in the assessment of disease activity in patients with juvenile idiopathic arthritis
Clara Malattia,Maria Beatrice Damasio,Curzio Basso,Alessandro Verri,Francesca Magnaguagno,Stefania Viola,Marco Gattorno,Angelo Ravelli,Paolo Tomà,Alberto Martini +9 more
TL;DR: DCE-MRI represents a promising method for the assessment of disease activity in JIA, especially in patients with wrist arthritis, and should be confirmed in large-scale longitudinal studies in view of its further application in therapeutic decision making and in clinical trials.
Journal ArticleDOI
3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural Networks.
Alice Fantazzini,Mario Esposito,Alice Finotello,Ferdinando Auricchio,Bianca Pane,Curzio Basso,Giovanni Spinella,Michele Conti +7 more
TL;DR: A deep learning-based pipeline is applied to automatically segment the CTA scans of the aortic lumen, from the ascending aorta to the iliac arteries, accounting for 3D spatial coherence, and shows that the proposed pipeline can effectively localize and segment the aortal lumen in subjects with aneurysm.
Proceedings ArticleDOI
Regularized 3D morphable models
TL;DR: This work introduces the new concept of regularized 3D morphable models, along with an iterative learning algorithm, by adding in the statistical model a noise/regularization term which is estimated from the examples set.
Proceedings ArticleDOI
Registration of expressions data using a 3D morphable model
TL;DR: This work presents a novel algorithm which breaks this restriction, allowing to register 3D scans of faces with arbitrary identity and expression, and can process incomplete data, yielding results which are both continuous and with low reconstruction error.