Metraipolis › archive › dc_4bbcc41db6db

DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision — arXiv:2609.09359

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09359
License (as archived): CC0-1.0
Archived: 2026-10-16T10:57:09.623Z
SHA-256 of the archived text: 54bfdc4e08e0f1947636508c9ec7a0e5458a3b92ba7e6f237a1348d1ec94f67a
Stable URL of this page: https://metraipolis.com/documento/dc_4bbcc41db6db

How to cite

DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision — arXiv:2609.09359 — arXiv (en), https://arxiv.org/abs/2609.09359 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bbcc41db6db (Metraipolis archive dc_4bbcc41db6db, sha256 54bfdc4e08e0f1947636508c9ec7a0e5458a3b92ba7e6f237a1348d1ec94f67a)

BibTeX

@misc{dc4bbcc41db6db,
  title = {DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision — arXiv:2609.09359},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09359},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bbcc41db6db; sha256 54bfdc4e08e0f1947636508c9ec7a0e5458a3b92ba7e6f237a1348d1ec94f67a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09359. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Polarimetric vision is gaining increasing attention because it provides physical cues about scene shape, material, and reflection that are difficult to recover from RGB alone. Recent work has therefore explored predicting polarization directly from conventional RGB images; however, the fidelity of these methods strongly depends on the polarization supervision used for training. Most existing datasets rely on Division-of-Focal-Plane (DoFP) cameras with four spatially interleaved analyzer orientations, which provide limited angular redundancy and introduce interpolation and instantaneous-field-of-view errors. We introduce DensePol, a high-redundancy RGB--polarization dataset based on Division-of-Time (DoT) acquisition, capturing 180 full-resolution analyzer orientations at $1^\circ$ intervals. DensePol contains 2,018 paired RGB--polarization images with the angular measurements and fitting residuals retained. Dense angular sampling substantially improves polarization stability, reducing AoLP deviation from $13.36^\circ$ to $2.21^\circ$. We further introduce a deterministic diffusion-based RGB-to-polarization framework with cyclic AoLP representation and a local DoLP refiner. Experiments demonstrate improved polarization prediction and downstream surface-normal estimation. The dataset and code will be publicly available.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.09359 — 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 2026-10-16T10:02:34.287Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).