dorsal/arxiv
View SchemaSVII-3D: Advancing Roadside Infrastructure Inventory with Decimeter-level 3D Localization and Comprehension from Sparse Street Imagery
| Authors | Chong Liu, Luxuan Fu, Yang Jia, Zhen Dong, Bisheng Yang |
|---|---|
| Categories | |
| ArXiv ID | 2601.10535vv1 |
| URL | https://arxiv.org/abs/2601.10535 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
The automated creation of digital twins and precise asset inventories is a critical task in smart city construction and facility lifecycle management. However, utilizing cost-effective sparse imagery remains challenging due to limited robustness, inaccurate localization, and a lack of fine-grained state understanding. To address these limitations, SVII-3D, a unified framework for holistic asset digitization, is proposed. First, LoRA fine-tuned open-set detection is fused with a spatial-attention matching network to robustly associate observations across sparse views. Second, a geometry-guided refinement mechanism is introduced to resolve structural errors, achieving precise decimeter-level 3D localization. Third, transcending static geometric mapping, a Vision-Language Model agent leveraging multi-modal prompting is incorporated to automatically diagnose fine-grained operational states. Experiments demonstrate that SVII-3D significantly improves identification accuracy and minimizes localization errors. Consequently, this framework offers a scalable, cost-effective solution for high-fidelity infrastructure digitization, effectively bridging the gap between sparse perception and automated intelligent maintenance.
{
"annotation_id": "f7dc3f5a-3374-44f3-b495-eb1d2892ee87",
"date_created": "2026-02-17T05:53:24.061000Z",
"date_modified": "2026-02-17T05:53:24.061000Z",
"file_hash": "96d6be2fead01d8d36c7994fa2258958c82204a29d26b0236dd2689633ddff6e",
"private": false,
"record": {
"abstract": "The automated creation of digital twins and precise asset inventories is a critical task in smart city construction and facility lifecycle management. However, utilizing cost-effective sparse imagery remains challenging due to limited robustness, inaccurate localization, and a lack of fine-grained state understanding. To address these limitations, SVII-3D, a unified framework for holistic asset digitization, is proposed. First, LoRA fine-tuned open-set detection is fused with a spatial-attention matching network to robustly associate observations across sparse views. Second, a geometry-guided refinement mechanism is introduced to resolve structural errors, achieving precise decimeter-level 3D localization. Third, transcending static geometric mapping, a Vision-Language Model agent leveraging multi-modal prompting is incorporated to automatically diagnose fine-grained operational states. Experiments demonstrate that SVII-3D significantly improves identification accuracy and minimizes localization errors. Consequently, this framework offers a scalable, cost-effective solution for high-fidelity infrastructure digitization, effectively bridging the gap between sparse perception and automated intelligent maintenance.",
"arxiv_id": "2601.10535",
"authors": [
"Chong Liu",
"Luxuan Fu",
"Yang Jia",
"Zhen Dong",
"Bisheng Yang"
],
"categories": [
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "SVII-3D: Advancing Roadside Infrastructure Inventory with Decimeter-level 3D Localization and Comprehension from Sparse Street Imagery",
"url": "https://arxiv.org/abs/2601.10535",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "9c1f73fe-f1a7-4581-b4eb-06f0d71267fc",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}