3D line segments not only enable lightweight representation of large-scale building point clouds but also contribute to enhanced contour accuracy in models. Moreover, they play an essential role in structural feature extraction, multimodal data registration, and scene semantic understanding. However, current 3D line segment extraction techniques still face challenges such as low accuracy, significant omissions, and difficulty in parameter selection. To address these issues, we propose a 3D line segment extraction workflow for architectural facades based on a neighbor weighted local centroid (NWLC) and a slicing strategy. Specifically, an adaptive centroid displacement amplification module based on NWLC is designed to achieve automated, robust, and complete contour point extraction. Subsequently, point cloud slicing combined with label connected component (LCC) analysis is employed to cluster contour points into line segment units. Finally, an inlier-outlier projection strategy is introduced to generate and optimize 3D line segments under architectural geometric regularization constraints. Extensive qualitative and quantitative evaluations are conducted on both public datasets–collected via TLS, MLS, ALS, and BIM–and self-acquired datasets. The results demonstrate that both the proposed contour point extraction and 3D line segment extraction algorithm outperform competing methods in terms of precision, robustness, and efficiency.