TSPconv-Net: Transformer and Sparse Convolution for 3D Instance Segmentation in Point Clouds

TSPconv-Net: Transformer and Sparse Convolution for 3D Instance Segmentation in Point Clouds

Current deep learning approaches for indoor 3D instance segmentation often rely on multilayer perceptrons (MLPs) for feature extraction. However, MLPs struggle to effectively capture the complex spatial relationships inherent in 3D scene data. To address this issue, we propose a novel and efficient...

Full description

Bibliographic Details
Main Authors: Xiaojuan Ning, Yule Liu, Yishu Ma, Zhiwei Lu, Haiyan Jin, Zhenghao Shi, Yinghui Wang 
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Mathematics
Subjects:
point clouds
indoor scenes
repetitive structures
instance segmentation
bounding boxes
Online Access:https://www.mdpi.com/2227-7390/12/18/2926

Internet

https://www.mdpi.com/2227-7390/12/18/2926

Similar Items