Please use this identifier to cite or link to this item:
Title: Structure-aware fusion network for 3D scene understanding
Authors: Yan, Haibin
Lv, Yating
Liong, Venice Erin
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Source: Yan, H., Lv, Y. & Liong, V. E. (2022). Structure-aware fusion network for 3D scene understanding. Chinese Journal of Aeronautics, 35(5), 194-203.
Journal: Chinese Journal of Aeronautics 
Abstract: In this paper, we propose a Structure-Aware Fusion Network (SAFNet) for 3D scene understanding. As 2D images present more detailed information while 3D point clouds convey more geometric information, fusing the two complementary data can improve the discriminative ability of the model. Fusion is a very challenging task since 2D and 3D data are essentially different and show different formats. The existing methods first extract 2D multi-view image features and then aggregate them into sparse 3D point clouds and achieve superior performance. However, the existing methods ignore the structural relations between pixels and point clouds and directly fuse the two modals of data without adaptation. To address this, we propose a structural deep metric learning method on pixels and points to explore the relations and further utilize them to adaptively map the images and point clouds into a common canonical space for prediction. Extensive experiments on the widely used ScanNetV2 and S3DIS datasets verify the performance of the proposed SAFNet.
ISSN: 1000-9361
DOI: 10.1016/j.cja.2021.07.012
Schools: Interdisciplinary Graduate School (IGS) 
Rights: © 2021 Chinese Society of Aeronautics and Astronautics. Production and hosting by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IGS Journal Articles

Files in This Item:
File Description SizeFormat 
1-s2.0-S1000936121002727-main.pdf1.69 MBAdobe PDFThumbnail

Citations 50

Updated on Sep 22, 2023

Web of ScienceTM
Citations 50

Updated on Sep 20, 2023

Page view(s)

Updated on Sep 23, 2023


Updated on Sep 23, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.