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
Posted Content
Learning shape correspondence with anisotropic convolutional neural networks
TL;DR: An intrinsic convolutional neural network architecture based on anisotropic diffusion kernels is introduced, which is term Anisotropic Convolutional Neural Network (ACNN), and is used to effectively learn intrinsic dense correspondences between deformable shapes in very challenging settings.
Proceedings ArticleDOI
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
TL;DR: In this paper, a deep residual network is proposed to learn dense correspondence between deformable 3D shapes by taking dense descriptor fields defined on two shapes as input, and outputs a soft map between the two given objects.
Proceedings ArticleDOI
Dense Non-rigid Shape Correspondence Using Random Forests
TL;DR: A shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations that achieves significant improvements over the baseline approach and obtains state-of-the-art results while keeping short computation times.
Proceedings ArticleDOI
Unsupervised Learning of Dense Shape Correspondence
TL;DR: This work introduces the first completely unsupervised correspondence learning approach for deformable 3D shapes, understanding that natural deformations approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions.
Journal ArticleDOI
Anisotropic diffusion descriptors
TL;DR: This paper shows how to construct direction‐sensitive spectral feature descriptors using anisotropic diffusion on meshes and point clouds, achieving results significantly better than state‐of‐the‐art methods.