FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Honghao, Xu, Juzhan, Huang, Zeyu, Xu, Pengfei, Huang, Hui, Hu, Ruizhen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916324622467072
author Xu, Honghao
Xu, Juzhan
Huang, Zeyu
Xu, Pengfei
Huang, Hui
Hu, Ruizhen
author_facet Xu, Honghao
Xu, Juzhan
Huang, Zeyu
Xu, Pengfei
Huang, Hui
Hu, Ruizhen
contents In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud. Existing methods typically rely on corner regression or box regression, which lack consideration for the global shapes of rooms. To address these issues, we propose a novel approach using a room-wise implicit representation with structural regularization to characterize the shapes of rooms in floorplans. By incorporating geometric priors of room layouts in floorplans into our training strategy, the generated room polygons are more geometrically regular. We have conducted experiments on two challenging datasets, Structured3D and SceneCAD. Our method demonstrates improved performance compared to state-of-the-art methods, validating the effectiveness of our proposed representation for floorplan reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation
Xu, Honghao
Xu, Juzhan
Huang, Zeyu
Xu, Pengfei
Huang, Hui
Hu, Ruizhen
Computer Vision and Pattern Recognition
Graphics
In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud. Existing methods typically rely on corner regression or box regression, which lack consideration for the global shapes of rooms. To address these issues, we propose a novel approach using a room-wise implicit representation with structural regularization to characterize the shapes of rooms in floorplans. By incorporating geometric priors of room layouts in floorplans into our training strategy, the generated room polygons are more geometrically regular. We have conducted experiments on two challenging datasets, Structured3D and SceneCAD. Our method demonstrates improved performance compared to state-of-the-art methods, validating the effectiveness of our proposed representation for floorplan reconstruction.
title FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.10687