Holistic Geometric Feature Learning for Structured Reconstruction

Ziqiong LuLinxi HuanQiyuan MaXianwei Zheng

Ziqiong LuLinxi HuanQiyuan MaXianwei Zheng

Sep 2023

0被引用

2笔记

开学季活动火爆进行中，iPad、蓝牙耳机、拍立得、键盘鼠标套装等你来拿

摘要原文

The inference of topological principles is a key problem in structured reconstruction. We observe that wrongly predicted topological relationships are often incurred by the lack of holistic geometry clues in low-level features. Inspired by the fact that massive signals can be compactly described with frequency analysis, we experimentally explore the efficiency and tendency of learning structure geometry in the frequency domain. Accordingly, we propose a frequency-domain feature learning strategy (F-Learn) to fuse scattered geometric fragments holistically for topology-intact structure reasoning. Benefiting from the parsimonious design, the F-Learn strategy can be easily deployed into a deep reconstructor with a lightweight model modification. Experiments demonstrate that the F-Learn strategy can effectively introduce structure awareness into geometric primitive detection and topology inference, bringing significant performance improvement to final structured reconstruction. Code and pre-trained models are available at https://github.com/Geo-Tell/F-Learn.