Metraipolis › archive › dc_4debbe9d583d
FAST: Flow Any Scene Transformer — arXiv:2609.39748
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39748
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:23.556Z
- SHA-256 of the archived text
e51555cab53a76f3e8024c8280936f0124ecf7ec9f27e9252377ea590cf2e162- Stable URL of this page
https://metraipolis.com/documento/dc_4debbe9d583d
How to cite
FAST: Flow Any Scene Transformer — arXiv:2609.39748 — arXiv (en), https://arxiv.org/abs/2609.39748 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4debbe9d583d (Metraipolis archive dc_4debbe9d583d, sha256 e51555cab53a76f3e8024c8280936f0124ecf7ec9f27e9252377ea590cf2e162)
BibTeX
@misc{dc4debbe9d583d,
title = {FAST: Flow Any Scene Transformer — arXiv:2609.39748},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39748},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4debbe9d583d; sha256 e51555cab53a76f3e8024c8280936f0124ecf7ec9f27e9252377ea590cf2e162},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39748. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene Transformer (FAST), a scalable correspondence model driven by two key insights. First, we reveal that the query-key projections inside single-view vision foundation models encode a coarse yet reusable prior for cross-view matching. Second, reusing these pretrained projections in cross-attention form yields a highly effective initialization for a ViT-based matcher built from a single-view encoder. Guided by these insights, we build FAST upon a vanilla single-view foundation model, utilizing a zero-parameter rewiring strategy to convert selected self-attention layers into cross-attention for cross-view interaction. This design allows ViT-based matchers to scale with advances in single-view foundation models, bypassing the need for a dedicated pair-centric pretraining stage. To fully unlock the scaling potential of this formulation, we assemble a 6-million-pair training corpus for general-purpose dense 2D displacement estimation across diverse co-visible image pairs. Extensive experiments demonstrate that FAST achieves state-of-the-art performance across a wide range of benchmarks, while scaling favorably with both backbone size and training data. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39748 — 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 2026-10-07T14:19:00.800Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).