Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path

TL;DR

Floor-SP introduces a novel optimization-based method for automated floorplan reconstruction from RGBD scans, leveraging sequential room-wise shortest path and deep learning to improve accuracy without relying on traditional corner detection.

Contribution

The paper presents a new optimization framework for floorplan reconstruction that does not require corner detection and handles non-Manhattan structures, outperforming existing methods.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of non-Manhattan floorplan structures.

Validated on 527 real-world RGBD scans.

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 dynamic programming 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 detection with thresholds, 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. Please refer to our project website http://jcchen.me/floor-sp/ for code and data.