Structure-aware fusion network for 3D scene understanding
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 v...
Saved in:
Main Authors: | Yan, Haibin, Lv, Yating, Liong, Venice Erin |
---|---|
Other Authors: | Interdisciplinary Graduate School (IGS) |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161283 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
TOWARDS DATASET CONSTRUCTION FOR 3D UNDERSTANDING
by: LI XINKE
Published: (2023) -
Granular3D: Delving into multi-granularity 3D scene graph prediction
by: HUANG, Kaixiang, et al.
Published: (2024) -
Multi-view fusion-based 3D object detection for robot indoor scene perception
by: Wang, Li, et al.
Published: (2020) -
TOWARDS LEARNING SCENE SEMANTICS ON 3D POINT CLOUDS
by: ZHAO NA
Published: (2021) -
Building information modelling (BIM) enhanced 3D concrete printing
by: Liu, Qinyan
Published: (2024)