# Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition

arXiv: https://arxiv.org/abs/2608.29929 · HTML: https://mlsanity.com/paper/2608.29929/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 29 of 29)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](https://mlsanity.com/paper/1506.08959/) (2015)
- [Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction](https://mlsanity.com/paper/2403.18795/) (2024)
- [BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance](https://mlsanity.com/paper/1703.00686/) (2017)
- [Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation](https://mlsanity.com/paper/2601.07671/) (2026)
- [Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark](https://mlsanity.com/paper/2505.06393/) (2025)
- [Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities](https://mlsanity.com/paper/2509.08302/) (2025)
- [LabelAny3D: Label Any Object 3D in the Wild](https://mlsanity.com/paper/2601.01676/) (2026)
- [LPLC: A Dataset for License Plate Legibility Classification](https://mlsanity.com/paper/2508.18425/) (2025)
- [Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition](https://mlsanity.com/paper/2604.05271/) (2026)
- [ICPR 2026 Competition on Low-Resolution License Plate Recognition](https://mlsanity.com/paper/2604.22506/) (2026)
- [Vehicle-centric Perception via Multimodal Structured Pre-training](https://mlsanity.com/paper/2512.19934/) (2025)
- [Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios](https://mlsanity.com/paper/2606.13625/) (2026)
- [Veri-Car: Towards Open-world Vehicle Information Retrieval](https://mlsanity.com/paper/2411.06864/) (2024)

## Abstract (arXiv)

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 https://github.com/UFPR-IPASPPR/3D-Vision-Benchmark/.