Semantic segmentation of large-scale point clouds with neighborhood uncertainty

• Published in: Multimedia tools and applications 2023-12, Vol.83 (21), p.60949-60964
• Main Authors: Bao, Yong, Wen, Haibiao, Zhang, Baoqing
• Format: Article
• Language: English
• Subjects: Computer Communication Networks; Computer Science; Computer vision; Data Structures and Information Theory; Image segmentation; Intelligence; Missing data; Multimedia Information Systems; Parameter estimation; Parameter uncertainty; Semantic segmentation; Semantics; Special Purpose and Application-Based Systems; Three dimensional models; Track 6: Computer Vision for Multimedia Applications; Virtual reality
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-17814-4

Large-scale point cloud segmentation is one of the important research directions in the field of computer vision, aiming at segmenting 3D point cloud data into parts with semantic meaning, which is widely used in the fields of robot perception, automated driving, and virtual reality. In practical applications, intelligences often face various uncertainties such as sensor noise, missing data, and uncertain model parameter estimation. However, many current research works do not consider the effects of these uncertainties, which can cause the model to overfit the noisy data and thus affect the model performance. In this paper, we propose a point cloud segmentation method with domain uncertainty that can greatly improve the robustness of the model to noise. Specifically, we first compute the neighborhood uncertainty, which is more reflective of the semantics of a local region than the prediction of a single point, which will reduce the impact of noise. Next, we fuse the uncertainty into the objective function, which allows the model to focus more on relatively deterministic data. Finally, we validate on the large-scale datasets S3DIS and Toronto3D, and the segmentation performance is substantially improved in both cases.