Structure-aware fusion network for 3D scene understanding

• المؤلفون الرئيسيون: Yan, Haibin, Lv, Yating, Liong, Venice Erin
• مؤلفون آخرون: Interdisciplinary Graduate School (IGS)
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Electrical and electronic engineering; 3D Point Clouds; Data Fusion
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/161283

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...