Abstract
This paper proposes a new approach for automated floorplan reconstruction from RGBD scans, a major milestone in indoor mapping research. The approach, dubbed Floor-SP, formulates a novel optimization problem, where room-wise coordinate descent sequentially solves shortest path problems to optimize the floorplan graph structure. The objective function consists of data terms guided by deep neural networks, consistency terms encouraging adjacent rooms to share corners and walls, and the model complexity term. The approach does not require corner/edge primitive extraction unlike most other methods. We have evaluated our system on production-quality RGBD scans of 527 apartments or houses, including many units with non-Manhattan structures. Qualitative and quantitative evaluations demonstrate a significant performance boost over the current state-of-the-art. We also share our code and data.
Paper
title={Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path},
author={Jiacheng Chen, Chen Liu, Jiaye Wu, Yasutaka Furukawa},
booktitle={The IEEE International Conference on Computer Vision (ICCV)},
year={2019}
}
Video
Code / Data
Check our code on our Github repo.
Update on Oct 28: 100 complete house scans have been released by Beike (www.ke.com) at this link. Please fill the form and download the data from Beike. A more detailed guideline on the data format will be provided soon. The 100 scans include the test set used in our paper, the IDs of the test scenes are provided in the Github repo. We will also provide a detailed step-by-step instruction on running Floor-SP on the released data.
Acknowledgement
This research is partially supported by National Science Foundation under grant IIS 1618685, NSERC Discovery Grants, NSERC Discovery Grants Accelerator Supplements, and DND/NSERC Discovery Grant Supplement. We thank Beike (www.ke.com) for the 3D house scans and annotations.