Metraipolis › archive › dc_349e26fe927f
Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition — arXiv:2608.29929
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29929
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:14.674Z
- SHA-256 of the archived text
49ed7872867cefd0a961fad8e3e47143e5c8cb1af3df03a75136af9d8872a2d4- Stable URL of this page
https://metraipolis.com/documento/dc_349e26fe927f
How to cite
Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition — arXiv:2608.29929 — arXiv (en), https://arxiv.org/abs/2608.29929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_349e26fe927f (Metraipolis archive dc_349e26fe927f, sha256 49ed7872867cefd0a961fad8e3e47143e5c8cb1af3df03a75136af9d8872a2d4)
BibTeX
@misc{dc349e26fe927f,
title = {Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition — arXiv:2608.29929},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29929},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_349e26fe927f; sha256 49ed7872867cefd0a961fad8e3e47143e5c8cb1af3df03a75136af9d8872a2d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vehicle attribute recognition is an important task in intelligent transportation systems, particularly when Automatic License Plate Recognition (ALPR) is unavailable or unreliable. Although vision foundation models have shown strong transferability across domains, their effectiveness for fine-grained vehicle classification remains underexplored. Moreover, given the inherently three-dimensional structure of vehicles, it is unclear whether emerging 3D-aware foundation models offer advantages over standard 2D architectures. This paper presents an empirical benchmark of 14 state-of-the-art 2D and 3D-aware vision foundation models. Using the challenging real-world UFPR-VeSV dataset, we evaluate these models as frozen feature extractors via linear probing for vehicle type, make, and model recognition. We further stress-test the best-performing models under few-shot learning and Out-of-Distribution (OOD) domain shifts. Our results show that standard 2D self-supervised models, particularly DINOv3, substantially outperform 3D-aware models in fine-grained tasks, achieving over 93% Macro-Accuracy for make and model recognition. However, the 3D-aware Depth Anything v2 exhibits stronger invariance to viewing angles in vehicle type classification. These findings motivate hybrid approaches that combine 2D and 3D priors for robust vehicle recognition. Our code is publicly available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29929 — 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 2026-10-17T09:28:48.093Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).