Metraipolis › archive › dc_2c3dbc9f69be
SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence — arXiv:2609.36545
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36545
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:13.957Z
- SHA-256 of the archived text
a48e400215b63071acac873e4144a9d11e7b11cbdf819b98b1f064d4e735c00c- Stable URL of this page
https://metraipolis.com/documento/dc_2c3dbc9f69be
How to cite
SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence — arXiv:2609.36545 — arXiv (en), https://arxiv.org/abs/2609.36545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c3dbc9f69be (Metraipolis archive dc_2c3dbc9f69be, sha256 a48e400215b63071acac873e4144a9d11e7b11cbdf819b98b1f064d4e735c00c)
BibTeX
@misc{dc2c3dbc9f69be,
title = {SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence — arXiv:2609.36545},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36545},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c3dbc9f69be; sha256 a48e400215b63071acac873e4144a9d11e7b11cbdf819b98b1f064d4e735c00c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dense feature matching between 360$^\circ$ panoramas underpins omnidirectional pose estimation, 3D reconstruction, and SLAM. Such panoramas are stored in the equirectangular projection (ERP), which unrolls the viewing sphere onto a flat chart and thereby introduces three distinct distortions -- a longitudinal seam (topology), latitude-dependent stretch (metric), and non-uniform pixel area (area) -- that the coarse stage of perspective-trained dense matchers does not model, so these matchers degrade systematically on ERP. We show that correcting the three distortions at the coarse-stage interfaces where they arise -- pairwise distortions in attention, per-pixel distortion in covisibility gating -- improves PCK@1$^\circ$ from 0.230 to 0.275 on Matterport3D under a fixed coarse scaffold, with the refiner architecture unchanged -- our central result. Concretely, SCCM (Spherically Consistent Coarse Matching) augments a chart-naive cross-attention/dual-softmax coarse matcher with two sphere-derived priors: Spherical Positional Attention (SPA) pairs a yaw-periodic RoPE (topology) with a tangent-plane bias (metric), and Area-Aware Covisibility (AAC) applies a pre-sigmoid log-area correction (area). The chart-naive scaffold serves as a controlled reference, separating the scaffold-replacement effect from the spherical-prior effect. Instantiated in the RoMa V1 framework with the same frozen encoder, refiner architecture, and loss, SCCM also outperforms the ERP-native EDM (0.163) and an ERP-retrained RoMa V1 (0.198) under a unified ERP dense matching protocol, while perspective-trained matchers largely fail on ERP. It further transfers zero-shot to Stanford2D3D and, when trained on outdoor Holo360D, leads there as well. 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/2609.36545 — 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 2026-10-07T18:04:24.711Z 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).