Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction Aykin, Yusuf Sachs, Hans Gerzen, Nikolai Sachs, Hans Computer Vision Architecture Building Construction Robotics in Construction ddc:600 This paper presents a robotic system developed to enhance automation in construction workflows through advanced AI and computer vision technologies. The system integrates a robotic arm with a 3D point cloud camera and state- of-the-art 2D pre-trained Deep Learning models, such as GroundingDINO and SegmentAnything, to detect and seg- ment construction elements in 3D dynamic, unstructured environments. By processing point cloud data from the cam- era and aligning it with real-world coordinates, the system achieves precise object localization, enabling tasks such as element handling and assembly. Designed to address chal- lenges like clutter, occlusion, and variability in construction sites, this system bridges the gap between controlled labora- tory conditions and real-world applications. Experimental evaluations highlight its potential to improve efficiency and adaptability in construction tasks. International Association for Automation and Robotics in Construction (IAARC) 2025 info:eu-repo/semantics/other doc-type:other text http://purl.org/coar/resource_type/c_1843 https://www.th-owl.de/elsa/record/14036 https://www.th-owl.de/elsa/download/14036/14039 Aykin Y, Sachs H, Gerzen N. <i>Enhancing Robotic Vision through Deep Learning Techniques: From Detection to Construction</i>. (Sachs H, ed.). International Association for Automation and Robotics in Construction (IAARC); 2025. doi:<a href="https://doi.org/10.22260/isarc2025/0026">10.22260/isarc2025/0026</a> eng info:eu-repo/semantics/altIdentifier/doi/10.22260/isarc2025/0026 info:eu-repo/semantics/altIdentifier/issn/2413-5844 info:eu-repo/semantics/openAccess