Metraipolis › archive › dc_a579a549ebba

CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment — arXiv:2610.40525

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40525
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:28.179Z
SHA-256 of the archived text
7cd9d4a636c485e5ab5bd675d7ed6a10280f3e4f4d48159c303a2e352675aadc
Stable URL of this page
https://metraipolis.com/documento/dc_a579a549ebba

How to cite

CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment — arXiv:2610.40525 — arXiv (en), https://arxiv.org/abs/2610.40525 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a579a549ebba (Metraipolis archive dc_a579a549ebba, sha256 7cd9d4a636c485e5ab5bd675d7ed6a10280f3e4f4d48159c303a2e352675aadc)
BibTeX
@misc{dca579a549ebba,
  title = {CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment — arXiv:2610.40525},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40525},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a579a549ebba; sha256 7cd9d4a636c485e5ab5bd675d7ed6a10280f3e4f4d48159c303a2e352675aadc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40525. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-modal scene and instance retrieval aims to retrieve a corresponding 3D environment or object given query 2D images, serving as a foundational mechanism for spatial reasoning in robotics and AR/VR. Existing methods achieve this by learning alignment only at the level of whole scenes or objects, which provides no supervision for the fine-grained local structure within them. In this work, we show that supervision on a set of sparse 2D-3D correspondences, without scene- or instance-level contrastive objectives, is sufficient to train a single model for both scene- and instance-level retrieval. Specifically, we propose $\textbf{CrossWeave}$, a novel framework for cross-modal retrieval that learns sparse patch-point alignment, which alone outperforms existing methods. An optimal transport-based aggregator over the aligned features gives further gains by clustering structurally redundant regions, freeing descriptor capacity for semantically distinct local features. CrossWeave achieves state-of-the-art performance on both scene- and instance-level retrieval on ScanNet and 3RScan with a $\textit{single model}$, whereas existing methods require separate models for each task. Our results suggest that whole-scene encoding is unnecessary for cross-modal retrieval and that sparse local correspondence supervision is a more effective and flexible alternative.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40525 — 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 2026-11-01T02:16:43.991Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).