Metraipolis › archive › dc_ef931fa4be4c

PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching — arXiv:2608.29819

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29819
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:08.964Z
SHA-256 of the archived text
f320bcd1f40ab2159aeba47ac1e27619b1575b5bfa8de20cba082222e7d8f2e1
Stable URL of this page
https://metraipolis.com/documento/dc_ef931fa4be4c

How to cite

PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching — arXiv:2608.29819 — arXiv (en), https://arxiv.org/abs/2608.29819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef931fa4be4c (Metraipolis archive dc_ef931fa4be4c, sha256 f320bcd1f40ab2159aeba47ac1e27619b1575b5bfa8de20cba082222e7d8f2e1)
BibTeX
@misc{dcef931fa4be4c,
  title = {PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching — arXiv:2608.29819},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29819},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef931fa4be4c; sha256 f320bcd1f40ab2159aeba47ac1e27619b1575b5bfa8de20cba082222e7d8f2e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues are often ambiguous or unreliable. To tackle this, we propose PhasorNet, a lightweight yet powerful framework that boosts geometric discrimination via frequency-domain cues. At its core, the Phase-Augmented Transformer (PAT) injects Fourier-derived phase information into the attention mechanism, yielding photometrically robust, structure-preserving features that prioritize structural consistency in difficult areas. Additionally, we develop a Geometry-Context Fusion Refinement Module (GCFRM) that combines a full-resolution convolutional stream with a lightweight attention-based stream (leveraging WQA and CDGA blocks) to efficiently preserve fine details and object boundaries without excessive overhead. Training is further enhanced by a multi-scale Edge-guided High-Error Region (EHR) loss that adaptively focuses optimization on high-error and edge regions, guiding hierarchical cost volume refinement. With only 5.3M parameters, PhasorNet achieves state-of-the-art performance on the challenging ETH3D benchmark while exhibiting excellent cross-domain generalization on KITTI, delivering an efficient and practical solution for accurate real-time stereo matching.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29819 — 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 2026-10-17T09:28:48.072Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).