G
Gemma Piella
Researcher at Pompeu Fabra University
Publications - 158
Citations - 5510
Gemma Piella is an academic researcher from Pompeu Fabra University. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 25, co-authored 143 publications receiving 4411 citations. Previous affiliations of Gemma Piella include Autonomous University of Barcelona & Polytechnic University of Catalonia.
Papers
More filters
Journal ArticleDOI
Survey on 3D face reconstruction from uncalibrated images
TL;DR: This work reviews 3D face reconstruction methods in the last decade, focusing on those that only use 2D pictures captured under uncontrolled conditions and observes that the deep learning strategy is rapidly growing since the last few years, matching its extension to that of the widespread statistical model fitting.
Book ChapterDOI
Temporal diffeomorphic free form deformation (TDFFD) applied to motion and deformation quantification of tagged MRI sequences
Mathieu De Craene,Catalina Tobon-Gomez,Constantine Butakoff,Nicolas Duchateau,Gemma Piella,Kawal Rhode,Alejandro F. Frangi +6 more
TL;DR: Strain quantification results obtained from the Tagged Magnetic Resonance Imaging (TMRI) sequences acquired for the 1st cardiac Motion Analysis Challenge (cMAC) are presented.
Proceedings ArticleDOI
An adaptive update lifting scheme with perfect reconstruction
TL;DR: An adaptive version of the lifting scheme which has the intriguing property that it allows perfect reconstruction without any overhead cost is proposed which restricts ourselves to the update lifting step which affects the approximation signal only.
Journal ArticleDOI
Learning non-linear patch embeddings with neural networks for label fusion.
Gerard Sanroma,Oualid Benkarim,Gemma Piella,Oscar Camara,Guorong Wu,Dinggang Shen,Juan Domingo Gispert,José Luis Molinuevo,Miguel Ángel González Ballester,Alzheimer’s Disease Neuroimaging Initiative +9 more
TL;DR: A framework to compute patch embeddings using neural networks so as to increase discriminative abilities of similarity‐based weighted voting in PBLF is proposed and compared with state‐of‐the‐art alternatives.
Journal ArticleDOI
Combining Seminorms in Adaptive Lifting Schemes and Applications to Image Analysis and Compression
TL;DR: This paper exploits the properties of seminorms to build lifting structures able to choose between different update filters, the choice being triggered by the local gradient-type features of the input.