We present a new framework for online dense 3D reconstruction of indoor scenes by using only depth sequences. This research is particularly useful in cases with a poor light condition or in a nearly featureless indoor environment. The lack of RGB information makes long-range camera pose estimation difficult in a large indoor environment. The key idea of our research is to take advantage of the geometric prior of Manhattan scenes in each stage of the reconstruction pipeline with the specific aim to reduce the cumulative registration error and overall odometry drift in a long sequence. This idea is further boosted by local Manhattan frame growing and the local-to-global strategy that leads to implicit loop closure handling for a large indoor scene. Our proposed pipeline, namely ManhattanFusion, starts with planar alignment and local pose optimization where the Manhattan constraints are imposed to create detailed local segments. These segments preserve intrinsic scene geometry by minimizing the odometry drift even under complex and long trajectories. The final model is generated by integrating all local segments into a global volumetric representation under the constraint of Manhattan frame-based registration across segments. Our algorithm outperforms others that use depth data only in terms of both the mean distance error and the absolute trajectory error, and it is also very competitive compared with RGB-D based reconstruction algorithms. Moreover, our algorithm outperforms the state-of-the-art in terms of the surface area coverage by 10-40 percent, largely due to the usefulness and effectiveness of the Manhattan assumption through the reconstruction pipeline.

We present an online framework for dense 3D reconstruction of indoor scenes using sequential Manhattan keyframes. We take advantage of the global geometry of indoor scenes extracted by Manhattan frames and pose optimization to enhance the accuracy and robustness of the reconstructed models. During sequential reconstruction, a Manhattan frame is extracted for each keyframe after surface normal adjustment, and used for a Manhattan keyframe-based planar alignment to initialize the surface registration while a pose graph optimization is used to refine camera poses. The final model is created by integrating the Manhattan keyframes into the unified volumetric model using refined pose estimations. Experimental results demonstrate the advantage of our geometry-based approach to reduce the cumulative registration error and overall geometric drift.

We propose an efficient 3D modeling method to support real-time volumetric reconstruction of indoor scenes based on sequential depth sequences captured from a RGB-D camera. Specifically, we want to reduce the cumulative error from sequential ICP registration due to noise and outliers in the depth data. We take advantage of the Manhattan frame assumption valid in most indoor scenes that can be used to facilitate large scale 3D surface registration. In our approach, the Manhattan frame is extracted from each depth frame and used for plane-to-plane frame alignment to initialize point-to-plane ICP surface registration. Experimental results on three different indoor datasets including LIDAR ground-truth data demonstrate the advantages of the proposed algorithm over the original ICP-based approaches to volumetric reconstruction.