Metraipolis › archive › dc_9014c07cd468
MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment — arXiv:2609.13691
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13691
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T01:52:42.848Z
- SHA-256 of the archived text
e3c38747a43186cc8bcfa479b93b64ea42b191053d2000ad121608bd3287757a- Stable URL of this page
https://metraipolis.com/documento/dc_9014c07cd468
How to cite
MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment — arXiv:2609.13691 — arXiv (en), https://arxiv.org/abs/2609.13691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9014c07cd468 (Metraipolis archive dc_9014c07cd468, sha256 e3c38747a43186cc8bcfa479b93b64ea42b191053d2000ad121608bd3287757a)
BibTeX
@misc{dc9014c07cd468,
title = {MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment — arXiv:2609.13691},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13691},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9014c07cd468; sha256 e3c38747a43186cc8bcfa479b93b64ea42b191053d2000ad121608bd3287757a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most existing visual odometry (VO) systems treat feature correspondences as deterministic measurements or assign uniform uncertainty, ignoring the inherent localization ambiguity of different observations. However, correspondence uncertainty is often anisotropic due to image structures such as edges, repetitive patterns, and motion blur, which can significantly affect geometric optimization. In this work, we propose MomentBA, a geometry-aware bundle adjustment framework that derives anisotropic correspondence uncertainty from second-order spatial moments of local similarity responses. Instead of introducing additional covariance prediction networks, the proposed method directly converts matching response distributions into interpretable covariance estimates and incorporates them into bundle adjustment as correspondence-specific information matrices for uncertainty-aware residual weighting. Furthermore, the proposed formulation is integrated into a differentiable optimization framework, establishing a direct connection between correspondence uncertainty and geometric estimation. Experiments on the EuRoC MAV and TartanAir v1 Hard datasets demonstrate that MomentBA improves monocular visual odometry accuracy compared with existing feature-based and learning-based approaches. The proposed anisotropic covariance model achieves lower rotational errors and more robust trajectory estimation than fixed and isotropic uncertainty models, validating the effectiveness of geometry-induced uncertainty modeling for challenging visual environments. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.13691 — 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 2026-10-16T01:25:23.516Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).