Metraipolis › archive › dc_27d00dd07757
Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps — arXiv:2611.05083
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05083
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:04:50.590Z
- SHA-256 of the archived text
d5bac7a9a7aeb955629f87a0fd7fb3395a1a98158e1fa96711fd9a5f82ede693- Stable URL of this page
https://metraipolis.com/documento/dc_27d00dd07757
How to cite
Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps — arXiv:2611.05083 — arXiv (en), https://arxiv.org/abs/2611.05083 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27d00dd07757 (Metraipolis archive dc_27d00dd07757, sha256 d5bac7a9a7aeb955629f87a0fd7fb3395a1a98158e1fa96711fd9a5f82ede693)
BibTeX
@misc{dc27d00dd07757,
title = {Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps — arXiv:2611.05083},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05083},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27d00dd07757; sha256 d5bac7a9a7aeb955629f87a0fd7fb3395a1a98158e1fa96711fd9a5f82ede693},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05083. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Estimating semantic correspondences between different object instances of similar categories in real-world images is a fundamental challenge in computer vision. While the recent progress in foundation models has significantly advanced solutions for such difficult image correspondence problems, respective methods are often insufficiently regularised. For example, common nearest-neighbour matching with foundation model features often results in noisy correspondences, which is particularly prominent when solving for dense correspondences. In this work, we tackle image matching via functional maps, which have been popularised for 3D shape matching due to their powerful spectral formalism utilising an efficient low-dimensional linear representation. However, functional maps require that domains (in our cases the rectangular image grids) are equipped with an informative and non-trivial geometry. To define a meaningful manifold structure for images, we use Galerkin's method from finite elements to derive a discrete Laplace-Beltrami operator (LBO) based on a manifold embedding of deep image features. Further, we leverage a neural adjoint map that allows to represent non-linear mappings. We demonstrate that our method sets the new state of the art among zero-shot image correspondence methods on multiple dense correspondence benchmarks of real-world images. Our code is publicly available: 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/2611.05083 — 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 2026-11-04T18:39:37.566Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).