E
Emanuele Rodolà
Researcher at Sapienza University of Rome
Publications - 151
Citations - 7272
Emanuele Rodolà is an academic researcher from Sapienza University of Rome. The author has contributed to research in topics: Shape analysis (digital geometry) & Computer science. The author has an hindex of 34, co-authored 120 publications receiving 5133 citations. Previous affiliations of Emanuele Rodolà include University of Tokyo & University of Lugano.
Papers
More filters
Journal ArticleDOI
Non-rigid puzzles
TL;DR: A non‐rigid multi‐part shape matching algorithm that simultaneously solves for the segmentation of the reference model, and for a dense correspondence to (subsets of) the parts.
Proceedings ArticleDOI
Elastic Net Constraints for Shape Matching
TL;DR: This work considers a parametrized relaxation of the widely adopted quadratic assignment problem (QAP) formulation for minimum distortion correspondence between deformable shapes and introduces a weighting parameter on the combination of two existing relaxations, namely spectral and game-theoretic.
Posted Content
ZoomOut: Spectral Upsampling for Efficient Shape Correspondence
TL;DR: It is shown that high quality maps can be obtained even if the input correspondences are noisy or are encoded by a small number of coefficients in a spectral basis, and the method is both robust to noisy input and scalable with respect to shape complexity.
Journal ArticleDOI
2-D Skeleton-Based Action Recognition via Two-Branch Stacked LSTM-RNNs
Danilo Avola,Marco Cascio,Luigi Cinque,Gian Luca Foresti,Cristiano Massaroni,Emanuele Rodolà +5 more
TL;DR: Comparisons on UT-Kinect and NTU-RGB+D datasets show that the accuracy of the proposed method is fully comparable to that of works based on 3D skeletons, which outperforms the current state-of-the-art.
Journal ArticleDOI
Fast and accurate surface alignment through an isometry-enforcing game
TL;DR: A novel technique that allows to obtain an accurate surface registration in a single step, without the need for an initial motion estimation, is proposed and outperforms the state of the art.