SPaM: soft patch matching for non-rigid pointcloud registration
3d reconstruction of deformable objects in dynamic scenes forms the fundamental basis of many robotic applications. Existing mesh-based approaches compromise registration accuracy, and lose important details due to interpolation and smoothing. Additionally, existing non-rigid registration techniques...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2023.1019579/full |
| _version_ | 1797778282702176256 |
|---|---|
| author | Behnam Maleki Raphael Falque Teresa Vidal-Calleja Alen Alempijevic |
| author_facet | Behnam Maleki Raphael Falque Teresa Vidal-Calleja Alen Alempijevic |
| author_sort | Behnam Maleki |
| collection | DOAJ |
| description | 3d reconstruction of deformable objects in dynamic scenes forms the fundamental basis of many robotic applications. Existing mesh-based approaches compromise registration accuracy, and lose important details due to interpolation and smoothing. Additionally, existing non-rigid registration techniques struggle with unindexed points and disconnected manifolds. We propose a novel non-rigid registration framework for raw, unstructured, deformable point clouds purely based on geometric features. The global non-rigid deformation of an object is formulated as an aggregation of locally rigid transformations. The concept of locality is embodied in soft patches described by geometrical properties based on SHOT descriptor and its neighborhood. By considering the confidence score of pairwise association between soft patches of two scans (not necessarily consecutive), a computed similarity matrix serves as the seed to grow a correspondence graph which leverages rigidity terms defined in As-Rigid-As-Possible for pruning and optimization. Experiments on simulated and publicly available datasets demonstrate the capability of the proposed approach to cope with large deformations blended with numerous missing parts in the scan process. |
| first_indexed | 2024-03-12T23:16:00Z |
| format | Article |
| id | doaj.art-fd7fc87a61ee4fee80f07d9577b1ad33 |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-03-12T23:16:00Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-fd7fc87a61ee4fee80f07d9577b1ad332023-07-17T10:55:20ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442023-07-011010.3389/frobt.2023.10195791019579SPaM: soft patch matching for non-rigid pointcloud registrationBehnam MalekiRaphael FalqueTeresa Vidal-CallejaAlen Alempijevic3d reconstruction of deformable objects in dynamic scenes forms the fundamental basis of many robotic applications. Existing mesh-based approaches compromise registration accuracy, and lose important details due to interpolation and smoothing. Additionally, existing non-rigid registration techniques struggle with unindexed points and disconnected manifolds. We propose a novel non-rigid registration framework for raw, unstructured, deformable point clouds purely based on geometric features. The global non-rigid deformation of an object is formulated as an aggregation of locally rigid transformations. The concept of locality is embodied in soft patches described by geometrical properties based on SHOT descriptor and its neighborhood. By considering the confidence score of pairwise association between soft patches of two scans (not necessarily consecutive), a computed similarity matrix serves as the seed to grow a correspondence graph which leverages rigidity terms defined in As-Rigid-As-Possible for pruning and optimization. Experiments on simulated and publicly available datasets demonstrate the capability of the proposed approach to cope with large deformations blended with numerous missing parts in the scan process.https://www.frontiersin.org/articles/10.3389/frobt.2023.1019579/fulldeformable registrationnon-rigid registrationsoft patchespatch matchingpointcloud registrationas rigid as possible |
| spellingShingle | Behnam Maleki Raphael Falque Teresa Vidal-Calleja Alen Alempijevic SPaM: soft patch matching for non-rigid pointcloud registration Frontiers in Robotics and AI deformable registration non-rigid registration soft patches patch matching pointcloud registration as rigid as possible |
| title | SPaM: soft patch matching for non-rigid pointcloud registration |
| title_full | SPaM: soft patch matching for non-rigid pointcloud registration |
| title_fullStr | SPaM: soft patch matching for non-rigid pointcloud registration |
| title_full_unstemmed | SPaM: soft patch matching for non-rigid pointcloud registration |
| title_short | SPaM: soft patch matching for non-rigid pointcloud registration |
| title_sort | spam soft patch matching for non rigid pointcloud registration |
| topic | deformable registration non-rigid registration soft patches patch matching pointcloud registration as rigid as possible |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2023.1019579/full |
| work_keys_str_mv | AT behnammaleki spamsoftpatchmatchingfornonrigidpointcloudregistration AT raphaelfalque spamsoftpatchmatchingfornonrigidpointcloudregistration AT teresavidalcalleja spamsoftpatchmatchingfornonrigidpointcloudregistration AT alenalempijevic spamsoftpatchmatchingfornonrigidpointcloudregistration |