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.

本文提出了一种 ' 粗到精 ' 的全局配准算法，通过利用较小尺度上的健壮配准来引导较大尺度上的新对应和结构约束，解决手持相机的 RGB-D 图像长视频序列全局一致 3D 模型重建的问题，并基于 SUN3D 数据集中的 25 个场景提供了规模达 10,401 个手动点击的点对应关系的基准测试，实验证明我们的算法比以前的方法更好。