Metraipolis › archive › dc_8aabda36623c

NHO: A Neural Hamiltonian Operator for Anchor-based Region Localization and Dense Correspondence — arXiv:2609.37048

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37048
License (as archived): CC0-1.0
Archived: 2026-10-07T18:40:51.283Z
SHA-256 of the archived text: 76e6a53e43498f2cc1ee62840218ecde41de590d5319fab78d5910f56bf27df9
Stable URL of this page: https://metraipolis.com/documento/dc_8aabda36623c

How to cite

NHO: A Neural Hamiltonian Operator for Anchor-based Region Localization and Dense Correspondence — arXiv:2609.37048 — arXiv (en), https://arxiv.org/abs/2609.37048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8aabda36623c (Metraipolis archive dc_8aabda36623c, sha256 76e6a53e43498f2cc1ee62840218ecde41de590d5319fab78d5910f56bf27df9)

BibTeX

@misc{dc8aabda36623c,
  title = {NHO: A Neural Hamiltonian Operator for Anchor-based Region Localization and Dense Correspondence — arXiv:2609.37048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8aabda36623c; sha256 76e6a53e43498f2cc1ee62840218ecde41de590d5319fab78d5910f56bf27df9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Non-rigid partial-to-full shape correspondence from sparse anchors requires identifying the corresponding region on the full surface and recovering dense correspondences between the partial shape and that region. We present NHO, which combines sparse anchors with the intrinsic geometry of the partial shape to learn a neural Hamiltonian operator whose localized eigenspace encodes both the region support and intrinsic coordinates for dense correspondence. NHO parameterizes the Hamiltonian potential as an intrinsic neural field and optimizes it using anchor evidence together with spectral and geometric constraints. To resolve the spatial ambiguity left by sparse anchors, we introduce reciprocal refinement between operator estimation and correspondence recovery. At each round, the current eigenspace provides spectral coordinates and restricts matching to its induced support, while geometrically reliable correspondences provide additional evidence for updating the potential. After refinement, aggregated eigenfunction energy yields the final localization, and the recovered map initializes dense correspondence refinement. Experiments demonstrate competitive accuracy on both tasks and robustness to uniform scaling and rotation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37048 — 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 2026-10-07T18:04:24.808Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).