Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching
Non-isometric shape correspondence remains a fundamental challenge in computer vision.
Traditional methods using Laplace-Beltrami operator (LBO) eigenmodes face limitations in …
Traditional methods using Laplace-Beltrami operator (LBO) eigenmodes face limitations in …
Bijective upsampling and learned embedding for point clouds correspondences
In this paper, we present a novel pipeline to compute and refine a data-driven solution for
estimating the correspondence between 3D point clouds. Our method is compatible with the …
estimating the correspondence between 3D point clouds. Our method is compatible with the …
Deformable shape matching with multiple complex spectral filter operator preservation
The functional maps framework has achieved remarkable success in non-rigid shape
matching. However, the traditional functional map representations do not explicitly encode …
matching. However, the traditional functional map representations do not explicitly encode …
[PDF][PDF] Adjoint Bijective ZoomOut: Efficient upsampling for learned linearly-invariant embedding
In this paper, we present a novel method for refining correspondences between 3D point
clouds. Our method is compatible with the functional map framework, so it relies on the …
clouds. Our method is compatible with the functional map framework, so it relies on the …