Interactive real-time scene acquisition from hand-held depth cameras has recently developed much momentum, enabling applications in ad-hoc object acquisition, augmented reality and other fields. A key challenge to online reconstruction remains error accumulation in the reconstructed camera trajectory, due to drift-inducing instabilities in the range scan alignments of the underlying iterative-closest-point (ICP) algorithm. Various strategies have been proposed to mitigate that drift, including SIFT-based pre-alignment, color-based weighting of ICP pairs, stronger weighting of edge features, and so on. In our work, we focus on surface curvature as a feature that is detectable on range scans alone and hence does not depend on accurate multi-sensor alignment. In contrast to previous work that took curvature into consideration, however, we treat curvature as an independent quantity that we consistently incorporate into every stage of the real-time reconstruction pipeline, including densely curvature-weighted ICP, range image fusion, local surface reconstruction, and rendering. Using multiple benchmark sequences, and in direct comparison to other state-of-the-art online acquisition systems, we show that our approach significantly reduces drift, both when analyzing individual pipeline stages in isolation, as well as seen across the online reconstruction pipeline as a whole.

Real-time or online 3D reconstruction has wide applicability and receives further interest due to availability of consumer depth cameras. Typical approaches use a moving sensor to accumulate depth measurements into a single model which is continuously refined. Designing such systems is an intricate balance between reconstruction quality, speed, spatial scale, and scene assumptions. Existing online methods either trade scale to achieve higher quality reconstructions of small objects/scenes. Or handle larger scenes by trading real-time performance and/or quality, or by limiting the bounds of the active reconstruction. Additionally, many systems assume a static scene, and cannot robustly handle scene motion or reconstructions that evolve to reflect scene changes. We address these limitations with a new system for real-time dense reconstruction with equivalent quality to existing online methods, but with support for additional spatial scale and robustness in dynamic scenes. Our system is designed around a simple and flat point-Based representation, which directly works with the input acquired from range/depth sensors, without the overhead of converting between representations. The use of points enables speed and memory efficiency, directly leveraging the standard graphics pipeline for all central operations, i.e., camera pose estimation, data association, outlier removal, fusion of depth maps into a single denoised model, and detection and update of dynamic objects. We conclude with qualitative and quantitative results that highlight robust tracking and high quality reconstructions of a diverse set of scenes at varying scales.