PrincetonComputer SciencePIXL GroupPublications → [Halber et al. 2017] Local Access
Fine-to-Coarse Global Registration of RGB-D Scans

CVPR, July 2017

Maciej Halber, Thomas Funkhouser

RGB-D scanning of indoor environments is important for many applications, including real estate, interior design, and virtual reality. However, it is still challenging to register RGB-D images from a hand-held camera over a long video sequence into a globally consistent 3D model. Current methods often can lose tracking or drift and thus fail to reconstruct salient structures in large environments (e.g., parallel walls in different rooms). To address this problem, we propose a "fine-to-coarse" global registration algorithm that leverages robust registrations at finer scales to seed detection and enforcement of new correspondence and structural constraints at coarser scales. To test global registration algorithms, we provide a benchmark with 10,401 manually-clicked point correspondences in 25 scenes from the SUN3D dataset. During experiments with this benchmark, we find that our fine-to-coarse algorithm registers long RGB-D sequences better than previous methods.

Maciej Halber and Thomas Funkhouser.
"Fine-to-Coarse Global Registration of RGB-D Scans."
CVPR, July 2017.


   author = "Maciej Halber and Thomas Funkhouser",
   title = "Fine-to-Coarse Global Registration of {RGB-D} Scans",
   journal = "CVPR",
   year = "2017",
   month = jul