no code implementations • 19 Mar 2024 • Nissim Maruani, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun
Although polygon meshes have been a standard representation in geometry processing, their irregular and combinatorial nature hinders their suitability for learning-based applications.
no code implementations • ICCV 2023 • Nissim Maruani, Roman Klokov, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun
In stark contrast to the case of images, finding a concise, learnable discrete representation of 3D surfaces remains a challenge.
no code implementations • 21 Oct 2019 • Kai Bai, Wei Li, Mathieu Desbrun, Xiaopei Liu
We propose a novel dictionary-based neural network which learns both a fast evaluation of sparse patch encoding and a dictionary of corresponding coarse and fine patches from a sequence of example simulations computed with any numerical solver.
Graphics
no code implementations • 23 Jun 2018 • Max Budninskiy, Glorian Yin, Leman Feng, Yiying Tong, Mathieu Desbrun
Our new geometric procedure exhibits the same strong resilience to noise as one of the staples of manifold learning, the Isomap algorithm, as it also exploits all pairwise geodesic distances to compute a low-dimensional embedding.
no code implementations • CVPR 2018 • Hao Fang, Florent Lafarge, Mathieu Desbrun
Interpreting 3D data such as point clouds or surface meshes depends heavily on the scale of observation.