Non-collaborative (i.e., reflective, transparent, metallic, etc.) surfaces are common in industrial production processes, where 3D reconstruction methods are applied for quantitative quality control inspections. Although the use or combination of photogrammetry and photometric stereo performs well for well-textured or partially textured objects, it usually produces unsatisfactory 3D reconstruction results on non-collaborative surfaces. To improve 3D inspection performances, this paper investigates emerging learning-based surface reconstruction methods, such as Neural Radiance Fields (NeRF), Multi-View Stereo (MVS), Monocular Depth Estimation (MDE), Gaussian Splatting (GS) and image-to-3D generative AI as potential alternatives for industrial inspections. A comprehensive evaluation dataset with several common industrial objects was used to assess methods and gain deeper insights into the applicability of the examined approaches for inspections in industrial scenarios. In the experimental evaluation, geometric comparisons were carried out between the reference data and learning-based reconstructions. The results indicate that no method can outperform all the others across all evaluations.

Autonomous mobile robotic solutions are increasingly being explored in precision agriculture to aid human workers in labour-intensive or repetitive tasks. Moreover, the emergence of foundation models in vision-based AI domain presents an opportunity to perform automated interpretation of in-field collected data. This study presents a cost-effective mobile robotic research platform designed for autonomous vineyard inspection: it integrates mission planning, real-world navigation and a post-processing pipeline of multimodal data. The system, based on the Leo rover, is equipped with LiDAR, RGB cameras and GNSS-visual-inertial positioning, ensuring reliable operation in GNSS-degraded vineyard environments. We propose a novel methodology for automating several stages of the workflow using various open and in-situ collected data. The robotic platform and processing pipeline were validated through simulation and field experiments, demonstrating its capability for autonomous navigation, 3D reconstruction, AI-based fruit detection and an initial plant health assessment through Large Multimodal Models (LMM). Results show that while 3D mapping provides highresolution spatial data, AI-driven object detection and vision models require further domain adaptation for reaching reliable and trustable operation. The study highlights the feasibility of cost-effective mobile robotic solutions in vineyard monitoring and the potential of integrating AI to enhance agricultural automation.

Road inspections are essential for assessing pavement conditions and planning maintenance to extend infrastructure lifespan. Cracks are key indicators of distress, and their timely detection can reduce repair costs. While manual inspections are costly and subjective, automated crack detection using vehicle-mounted cameras and digital image processing has improved efficiency but still requires extensive manual review. Crack detection research typically focuses on improving the accuracy of the detection and feature extraction, neglecting the geospatial mapping part which is essential in pavement inspection. This paper presents an end-to-end pipeline that combines V-SLAM, deep learning (DL) and 2D-3D mapping to detect and map pavement cracks using vehicle-mounted cameras footage and provide georeferenced results interpretable inside a Geospatial Information System (GIS). Results significantly reduce inspection time by providing preliminary detections for rapid verification by expert operators in GIS environments. This enhances data management, efficient validation, advanced spatial analysis and time-based tracking of crack progression, ensuring informed decision-making and optimized maintenance planning, ultimately extending infrastructure lifespan and reducing costs.