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

TL;DR

FRI-Net is a new approach for 2D floorplan reconstruction from 3D point clouds that uses room-wise implicit representations and geometric priors to improve accuracy and regularity of room shapes.

Contribution

It introduces a novel room-wise implicit representation with structural regularization for better floorplan reconstruction from 3D data.

Findings

Outperforms state-of-the-art methods on Structured3D and SceneCAD datasets.

Produces more geometrically regular and accurate room polygons.

Validates the effectiveness of room-wise implicit representation.

Abstract

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.