WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration

Autor: Lei Li, Hongbo Fu, Maks Ovsjanikov

Publikováno v: IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Visualization and Computer Graphics, 2022
IEEE Transactions on Visualization and Computer Graphics (TVCG)

In this work, we present a novel method called WSDesc to learn 3D local descriptors in a weakly supervised manner for robust point cloud registration. Our work builds upon recent 3D CNN-based descriptor extractors, which leverage a voxel-based repres

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2625d11de68b93adfb123736f8b0f4d1
https://doi.org/10.1109/tvcg.2022.3160005

DiffusionNet: Discretization Agnostic Learning on Surfaces

Autor: Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov

Publikováno v: ACM Transactions on Graphics
ACM Transactions on Graphics, 2022, 41 (3), pp.1-16. ⟨10.1145/3507905⟩
Transactions on Graphics

We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution an

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8519806d663cc59ff8ba3a89158e65cf
https://doi.org/10.1145/3507905

Physical Simulation Layer for Accurate 3D Modeling

Autor: Mariem Mezghanni, Theo Bodrito, Malika Boulkenafed, Maks Ovsjanikov

Publikováno v: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0cf2d5b68285df3cafdcbced04a28bb7
https://doi.org/10.1109/cvpr52688.2022.01315

Learning Spectral Unions of Partial Deformable 3D Shapes

Autor: Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà

Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian spectrum as a compact, isometry and permutation-invariant representation of a shape. Some recent w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47d9e7b6189b6331944ae75c2f1fc57b
https://hdl.handle.net/10278/5002939

Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis

Autor: Jing Ren, Biao Zhang, Bojian Wu, Jianqiang Huang, Lubin Fan, Maks Ovsjanikov, Peter Wonka

We propose a novel and flexible roof modeling approach that can be used for constructing planar 3D polygon roof meshes. Our method uses a graph structure to encode roof topology and enforces the roof validity by optimizing a simple but effective plan

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0b0022824b07b7b0edfa47f72539332
http://arxiv.org/abs/2109.07683