A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
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 handheld 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"doi:10.1109/cvpr.2017.705 dblp:conf/cvpr/HalberF17 fatcat:ok2vsj6shrgwvmhc42mi5poxtq