Metraipolis › archive › dc_c4e70f110d42

GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision — arXiv:2611.07677

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07677
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:30.180Z
SHA-256 of the archived text
85cc691ad57e15cdaf21e0714078f24bf721dcd04e6aa856148623cb5e076cf4
Stable URL of this page
https://metraipolis.com/documento/dc_c4e70f110d42

How to cite

GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision — arXiv:2611.07677 — arXiv (en), https://arxiv.org/abs/2611.07677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4e70f110d42 (Metraipolis archive dc_c4e70f110d42, sha256 85cc691ad57e15cdaf21e0714078f24bf721dcd04e6aa856148623cb5e076cf4)
BibTeX
@misc{dcc4e70f110d42,
  title = {GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision — arXiv:2611.07677},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07677},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4e70f110d42; sha256 85cc691ad57e15cdaf21e0714078f24bf721dcd04e6aa856148623cb5e076cf4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Point clouds represent 3D object geometry as sets of spatial coordinates. A fundamental task in their analysis is keypoint detection, i.e., identifying a sparse subset of points that captures the most salient features. While supervised methods rely on manual annotations, unsupervised approaches leverage intrinsic geometric properties to localize keypoints without human input. We introduce GEKey, a self-supervised framework that uses the geodesic eccentricity transform, an SE(3)-invariant geometric measure, to identify instance-specific salient points. These points serve as pseudo-labels to train a model that aligns its predictions with the object's intrinsic structure. GEKey is simple, efficient, and robust, preserving intra-class variation by balancing instance-specific and category-level structure. Extensive experiments on ShapeNetCoreV2, KeypointNet, CAPE, ITOP, and DeformingThings4D show state-of-the-art performance in both keypoint detection and alignment, with strong resilience to noise, downsampling, deformations, and real-world conditions. The code and pretrained models are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.07677 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:25:42.615Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).