TL;DR
This paper introduces a new method that uses 2D floorplans to efficiently align panorama RGBD scans at building scale, reducing the need for dense sampling and improving large indoor space mapping.
Contribution
It presents the first effective system leveraging 2D floorplans for building-scale 3D pointcloud alignment, with novel multi-modal cues and a coverage potential to improve accuracy.
Findings
Successfully applied to five large indoor spaces
Reduces the number of scans needed for alignment
Outperforms traditional scan-to-scan methods
Abstract
This paper presents a novel algorithm that utilizes a 2D floorplan to align panorama RGBD scans. While effective panorama RGBD alignment techniques exist, such a system requires extremely dense RGBD image sampling. Our approach can significantly reduce the number of necessary scans with the aid of a floorplan image. We formulate a novel Markov Random Field inference problem as a scan placement over the floorplan, as opposed to the conventional scan-to-scan alignment. The technical contributions lie in multi-modal image correspondence cues (between scans and schematic floorplan) as well as a novel coverage potential avoiding an inherent stacking bias. The proposed approach has been evaluated on five challenging large indoor spaces. To the best of our knowledge, we present the first effective system that utilizes a 2D floorplan image for building-scale 3D pointcloud alignment. The source…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
