Metraipolis › archive › dc_bb3d8b7f01dd

ZipMVS: Multi-View Stereo with Compressed Cost Volumes — arXiv:2608.28033

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28033
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:07.053Z
SHA-256 of the archived text
86460f3aac571bc7af88afb39b630c8babfbd8bc687955dcab39b8f3f6c62d3b
Stable URL of this page
https://metraipolis.com/documento/dc_bb3d8b7f01dd

How to cite

ZipMVS: Multi-View Stereo with Compressed Cost Volumes — arXiv:2608.28033 — arXiv (en), https://arxiv.org/abs/2608.28033 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb3d8b7f01dd (Metraipolis archive dc_bb3d8b7f01dd, sha256 86460f3aac571bc7af88afb39b630c8babfbd8bc687955dcab39b8f3f6c62d3b)
BibTeX
@misc{dcbb3d8b7f01dd,
  title = {ZipMVS: Multi-View Stereo with Compressed Cost Volumes — arXiv:2608.28033},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28033},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb3d8b7f01dd; sha256 86460f3aac571bc7af88afb39b630c8babfbd8bc687955dcab39b8f3f6c62d3b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28033. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple registered RGB images, thanks to the highly informative, geometric constraints between them. However, their substantial memory requirements remain a major obstacle for deployment in domains such as aerospace and autonomous systems, where resource efficiency is critical. In this work, we introduce ZipMVS, an MVS method specifically designed for efficient high-quality reconstruction. We propose a novel depth-hypothesis strategy that enables substantial compression of the cost volume, hence greatly reducing GPU memory consumption while preserving reconstruction accuracy. Experiments on the DTU and Tanks and Temples datasets show that ZipMVS achieves competitive reconstruction quality compared with other efficiency-oriented MVS methods, while achieving a competitive balance between reconstruction quality and GPU memory usage. The code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28033 — 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 2026-10-17T11:10:05.294Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).