Metraipolis › archive › dc_73a3914bfadb
Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach — arXiv:2610.21802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:35:30.817Z
- SHA-256 of the archived text
0634be686997a26fa96156c402d7227707fea22c72412f688c3cfda371401c36- Stable URL of this page
https://metraipolis.com/documento/dc_73a3914bfadb
How to cite
Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach — arXiv:2610.21802 — arXiv (en), https://arxiv.org/abs/2610.21802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73a3914bfadb (Metraipolis archive dc_73a3914bfadb, sha256 0634be686997a26fa96156c402d7227707fea22c72412f688c3cfda371401c36)
BibTeX
@misc{dc73a3914bfadb,
title = {Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach — arXiv:2610.21802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73a3914bfadb; sha256 0634be686997a26fa96156c402d7227707fea22c72412f688c3cfda371401c36},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Partial shape matching is a crucial yet underexplored problem in 3D vision, with significant relevance to real-world scenarios where shapes are often only partially observed. Existing feature descriptors face difficulties in this setting, as traditional representations either struggle with the boundaries of partial shapes or heavily depend on the shape's spatial position. While existing approaches have employed DINO features for partial shape matching, these features are not inherently suited for handling partial observations. In this work, we propose a method to refine DINO features using LoRA-based self-supervised learning, enabling the generation of feature descriptors that are robust to partiality. Our features substantially improve performance on partial shape matching compared to traditional or vision foundation features. Additionally, when integrated into existing partial shape matching pipelines, we achieve state-of-the-art results on partial shape matching and left-right prediction benchmarks. 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/2610.21802 — 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 2026-10-16T08:52:02.701Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).