Metraipolis › archive › dc_a54e28f951cd

Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds — arXiv:2609.32789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32789
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:04.904Z
SHA-256 of the archived text
05a1839f6ced244d1bdcf2ceaa5779657f6acb59563f66078090c9b983e58087
Stable URL of this page
https://metraipolis.com/documento/dc_a54e28f951cd

How to cite

Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds — arXiv:2609.32789 — arXiv (en), https://arxiv.org/abs/2609.32789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a54e28f951cd (Metraipolis archive dc_a54e28f951cd, sha256 05a1839f6ced244d1bdcf2ceaa5779657f6acb59563f66078090c9b983e58087)
BibTeX
@misc{dca54e28f951cd,
  title = {Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds — arXiv:2609.32789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a54e28f951cd; sha256 05a1839f6ced244d1bdcf2ceaa5779657f6acb59563f66078090c9b983e58087},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large-scale point cloud representations of complex geome tries incur prohibitive computational and memory costs, necessitating compressed implicit representations. To ad dress this, we propose a unified framework comprising im plicit geometric field representation, hierarchical frequency domain compression, and conditional high-frequency predic tion. Specifically, an unordered point cloud is mapped to an implicit field defined within its physical bounding box. A smooth Fourier pyramid is then constructed, where com pact low-frequency components capture the global geometry. Inter-scale high-frequency residuals are encoded to preserve the spatial information required for reconstructing fine geo metric details. To restore the high-frequency information lost during compression, we develop a hierarchical 3D neural net work. The reconstructed implicit field is converted back into a point cloud through isosurface extraction. Experiments on a complex-boundary point cloud with more than eight mil lion points demonstrate that the proposed method achieves a higher compression ratio than existing point cloud compres sion methods while maintaining comparable reconstruction quality.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.32789 — 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 2026-10-07T23:29:27.098Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).