Semantic segmentation-assisted instance feature fusion for multi-level 3D part instance segmentation
作者机构:Institute for Advanced StudyTsinghua UniversityBeijing 100084China Microsoft Research AsiaBeijing 100080China
出 版 物:《Computational Visual Media》 (计算可视媒体(英文版))
年 卷 期:2023年第9卷第4期
页 面:699-715页
核心收录:
学科分类:0710[理学-生物学] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:3D part instance segmentation feature fusion 3D deep learning
摘 要:Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding.Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances.In this paper,we present a new method for 3D part instance segmentation.Our method exploits semantic segmentation to fuse nonlocal instance features,such as center prediction,and further enhances the fusion scheme in a multi-and cross-level way.We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points.Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark.We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.