Metraipolis › archive › dc_f0a20eeefd68
NIF: Normal-Intersection Fields for Geometrically Consistent Oriented Box Refinement — arXiv:2610.39715
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39715
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:42:08.534Z
- SHA-256 of the archived text
9eae77e6c1f1494ed842b6650c4ccd2cdfc021d0a9fe2adf1cef440b1e6fb84d- Stable URL of this page
https://metraipolis.com/documento/dc_f0a20eeefd68
How to cite
NIF: Normal-Intersection Fields for Geometrically Consistent Oriented Box Refinement — arXiv:2610.39715 — arXiv (en), https://arxiv.org/abs/2610.39715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0a20eeefd68 (Metraipolis archive dc_f0a20eeefd68, sha256 9eae77e6c1f1494ed842b6650c4ccd2cdfc021d0a9fe2adf1cef440b1e6fb84d)
BibTeX
@misc{dcf0a20eeefd68,
title = {NIF: Normal-Intersection Fields for Geometrically Consistent Oriented Box Refinement — arXiv:2610.39715},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39715},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0a20eeefd68; sha256 9eae77e6c1f1494ed842b6650c4ccd2cdfc021d0a9fe2adf1cef440b1e6fb84d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accurate oriented detection requires a box to follow object boundaries, yet a standard regression head predicts its center, size, and angle from a pooled region representation. Small errors in these coupled parameters can displace long boundaries even when the object is correctly classified. We propose NIF, a refinement module that replaces an additional box regressor with normal-intersection fields. Given a coarse oriented box, the module observes local features at 20 boundary anchors and predicts signed distances along their outward normals. These observations admit an exact affine representation in five geometric variables. A differentiable, reliability-weighted least-squares fit projects the predicted field onto this representation and analytically recovers a refined rectangle. Tangential pooling preserves the normal position profile, while shared projection limits the added network to 0.132M parameters. On DOTA-v1.0, NIF reaches 78.00%, 79.11%, and 79.02% mAP with Oriented R-CNN, LSKNet-S, and Strip R-CNN, respectively, achieving the highest single-scale SOTA result in Table 1. It reaches 68.19% on DIOR-R, improves matched FAIR1M/DIOR-R baselines by 0.30/0.68%, and raises HRSC mean IoU from 0.867 to 0.888 while reducing field error by 24.5%. Across four different detector frameworks with the detectors frozen, relative AP75 improves by 1.57-4.18% and COCO-style mAP by 0.42-3.74%, without detector retraining. Code is available at 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/2610.39715 — 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 2026-11-01T02:16:43.949Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).