%0 Conference Paper %F Oral %T DWKS : A Local Descriptor of Deformations Between Meshes and Point Clouds %+ Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX) %+ Institut Polytechnique de Paris (IP Paris) %A Magnet, Robin %A Ovsjanikov, Maks %< avec comité de lecture %3 2021 IEEE/CVF International Conference on Computer Vision (ICCV) %B 2021 IEEE/CVF International Conference on Computer Vision (ICCV) %C Montreal, Canada %I IEEE %P 3773-3782 %8 2021-10-10 %D 2021 %R 10.1109/ICCV48922.2021.00377 %Z Computer Science [cs] %Z Computer Science [cs]/Artificial Intelligence [cs.AI] %Z Mathematics [math]/Differential Geometry [math.DG] %Z Mathematics [math]Conference papers %X We propose a novel pointwise descriptor, called DWKS, aimed at finding correspondences across two deformable shape collections. Unlike the majority of existing descriptors, rather than capturing local geometry, DWKS captures the deformation around a point within a collection in a multi-scale and informative manner. This, in turn, allows to compute inter-collection correspondences without using landmarks. To this end, we build upon the successful spectral WKS descriptors, but rather than using the Laplace-Beltrami operator, show that a similar construction can be performed on shape difference operators, that capture differences or distortion within a collection. By leveraging the collection information our descriptor facilitates difficult non-rigid shape matching tasks, even in the presence of strong partiality and significant deformations. We demonstrate the utility of our approach across a range of challenging matching problems on both meshes and point clouds. The code for this paper can be found at https://github.com/RobinMagnet/DWKS %G English %2 https://polytechnique.hal.science/hal-03607804/document %2 https://polytechnique.hal.science/hal-03607804/file/DWKS_ICCV21.pdf %L hal-03607804 %U https://polytechnique.hal.science/hal-03607804 %~ X %~ CNRS %~ LIX %~ INSMI %~ X-LIX %~ X-DEP %~ X-DEP-INFO %~ IP_PARIS %~ IP_PARIS_COPIE