FRI-Net: Floorplan Reconstruction via 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.

Cite

Text

Xu et al. "FRI-Net: Floorplan Reconstruction via Room-Wise Implicit Representation." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73411-3_1

Markdown

[Xu et al. "FRI-Net: Floorplan Reconstruction via Room-Wise Implicit Representation." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/xu2024eccv-frinet/) doi:10.1007/978-3-031-73411-3_1

BibTeX

@inproceedings{xu2024eccv-frinet,
  title     = {{FRI-Net: Floorplan Reconstruction via Room-Wise Implicit Representation}},
  author    = {Xu, Honghao and Xu, Juzhan and Huang, Zeyu and Xu, Pengfei and Huang, Hui and Hu, Ruizhen},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-73411-3_1},
  url       = {https://mlanthology.org/eccv/2024/xu2024eccv-frinet/}
}