🤖 AI Summary
This paper addresses two core challenges: the difficulty of transferring semantic information from 2D images to 3D point clouds, and the disconnection between implicit guidance and explicit modeling. It is the first work to systematically characterize semantics in point clouds as serving dual roles—implicit decision guidance and explicit structural modeling—and establishes a cross-task semantic fusion taxonomy spanning autonomous driving, surveying, and architecture. The authors propose a unified analytical framework integrating multimodal alignment, 3D semantic segmentation, scene graph reasoning, and cross-domain transfer learning, validated through comparative experiments on mainstream public benchmarks. Contributions include: (1) a structured literature repository; (2) a continuously updated GitHub resource platform; and (3) a standardized review benchmark and practical guideline for semantic point cloud research—providing both theoretical foundations and technical references for future method development and real-world deployment.
📝 Abstract
Point clouds, a prominent method of 3D representation, are extensively utilized across industries such as autonomous driving, surveying, electricity, architecture, and gaming, and have been rigorously investigated for their accuracy and resilience. The extraction of semantic information from scenes enhances both human understanding and machine perception. By integrating semantic information from two-dimensional scenes with three-dimensional point clouds, researchers aim to improve the precision and efficiency of various tasks. This paper provides a comprehensive review of the diverse applications and recent advancements in the integration of semantic information within point clouds. We explore the dual roles of semantic information in point clouds, encompassing both implicit guidance and explicit representation, across traditional and emerging tasks. Additionally, we offer a comparative analysis of publicly available datasets tailored to specific tasks and present notable observations. In conclusion, we discuss several challenges and potential issues that may arise in the future when fully utilizing semantic information in point clouds, providing our perspectives on these obstacles. The classified and organized articles related to semantic based point cloud tasks, and continuously followed up on relevant achievements in different fields, which can be accessed through https://github.com/Jasmine-tjy/Semantic-based-Point-Cloud-Tasks.