Metraipolis › archive › dc_723798477dc4
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation — arXiv:2609.38856
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38856
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:35.994Z
- SHA-256 of the archived text
9c5d2a2b60ba20dfd8824e04c21ff1eb05c65bf18e43e9d3da76fb9e8df8a9ff- Stable URL of this page
https://metraipolis.com/documento/dc_723798477dc4
How to cite
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation — arXiv:2609.38856 — arXiv (en), https://arxiv.org/abs/2609.38856 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_723798477dc4 (Metraipolis archive dc_723798477dc4, sha256 9c5d2a2b60ba20dfd8824e04c21ff1eb05c65bf18e43e9d3da76fb9e8df8a9ff)
BibTeX
@misc{dc723798477dc4,
title = {Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation — arXiv:2609.38856},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38856},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_723798477dc4; sha256 9c5d2a2b60ba20dfd8824e04c21ff1eb05c65bf18e43e9d3da76fb9e8df8a9ff},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38856. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.38856 — 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 2026-10-07T14:19:00.627Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).