Deployable 3D Semantic Segmentation for AI-Assisted Bridge Inspection: Benchmarking Modern Point-Cloud Models Under an 8 GB GPU Constraint
AI-powered damage identification and condition assessment of civil infrastructure increasingly rely on accurate semantic understanding of three-dimensional sensing data. In bridge inspection and post-disaster assessment, component-level semantic segmentation of point clouds provides essential structural context for localizing and interpreting potential damage. However, modern 3D segmentation models are often evaluated mainly by accuracy under high-end computing environments, whereas field-oriented damage assessment may require local processing with limited computational resources. This paper studies deployable 3D semantic segmentation for real-world bridge point clouds under an explicit 8 GB dedicated-VRAM single-GPU constraint. We benchmark representative architectures on five heterogeneous bridge datasets, reporting not only mIoU and overall accuracy but also training time, peak GPU memory, and cross-dataset generalization to a post-disaster bridge dataset. The results show that deployability is not determined by model capacity, memory footprint, or single-dataset accuracy alone; instead, practical deployment for AI-assisted infrastructure inspection and damage-assessment workflows requires a balance of accuracy, runtime, memory use, and robustness to domain variation.
Authors
- Kenta Itakura (ORCID: https://orcid.org/0000-0001-7259-271X)
- Pang‐jo Chun (ORCID: https://orcid.org/0000-0002-9755-8435)
- Takumi Murai
- Seiya Orimoto
Institutions
- The University of Tokyo (JP)
Publication Details
- Journal
- Infrastructures
- Published
- 2026-11-17
- DOI
- https://doi.org/10.3390/infrastructures11110425
- Primary Topic
- Infrastructure Maintenance and Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Japan Construction Information Center
- Council for Science, Technology and Innovation
- Japan Society for the Promotion of Science