Metraipolis › archive › dc_ff27db2d55b7
MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model — arXiv:2608.20639
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20639
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:49:28.574Z
- SHA-256 of the archived text
8e0b0f3a969283ac06f0ef89d70458adc848a6943d7e3367ddbdbeb90cbe5d96- Stable URL of this page
https://metraipolis.com/documento/dc_ff27db2d55b7
How to cite
MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model — arXiv:2608.20639 — arXiv (en), https://arxiv.org/abs/2608.20639 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff27db2d55b7 (Metraipolis archive dc_ff27db2d55b7, sha256 8e0b0f3a969283ac06f0ef89d70458adc848a6943d7e3367ddbdbeb90cbe5d96)
BibTeX
@misc{dcff27db2d55b7,
title = {MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model — arXiv:2608.20639},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20639},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff27db2d55b7; sha256 8e0b0f3a969283ac06f0ef89d70458adc848a6943d7e3367ddbdbeb90cbe5d96},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20639. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt a unified framework that projects 2D image features into a 3D world space and aggregates them into a single feature. Although they are effective, they struggle to generalize to unseen camera configurations during training due to two main issues. First, they are difficult to capture accurate visual geometry across views in unseen camera configurations. Second, they make detection models highly dependent on distortion patterns during training arising from their image feature projection. To address these, we leverage a visual geometric foundation model and propose MV2GF. This foundation model has exhibited strong generalization in capturing visual geometry across views and predicting accurate 3D attributes in diverse camera configurations. MV2GF fuses task-specific features with general-purpose geometric features extracted by the foundation model to effectively capture the visual geometry even in unseen camera configurations. Furthermore, MV2GF projects each pixel in the image features to an appropriate 3D location using 3D pointmaps predicted by the foundation model, preventing the detection model from depending on distortion patterns during training. Our experiments demonstrate the effectiveness of leveraging a visual geometric foundation model for MVPD and that MV2GF generalizes better than existing methods. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20639 — 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 2026-10-18T10:48:13.548Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).