Comprehensive Use of Curvature For Robust And Accurate Online Surface Reconstruction

Abstract

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.

Citation Style:    Display Alpha ACM SIGGRAPH IEEEtran Publication

Comprehensive Use of Curvature For Robust And Accurate Online Surface Reconstruction. Damien Lefloch, Markus Kluge, Hamed Sarbolandi, Tim Weyrich, Andreas Kolb. In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 39(12), pp. 2349–2365, 2017.Damien Lefloch, Markus Kluge, Hamed Sarbolandi, Tim Weyrich, and Andreas Kolb. Comprehensive use of curvature for robust and accurate online surface reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 39(12):2349–2365, December 2017.Lefloch, D., Kluge, M., Sarbolandi, H., Weyrich, T., and Kolb, A. 2017. Comprehensive use of curvature for robust and accurate online surface reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 39, 12 (Dec.), 2349–2365.D. Lefloch, M. Kluge, H. Sarbolandi, T. Weyrich, and A. Kolb, “Comprehensive use of curvature for robust and accurate online surface reconstruction,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 39, no. 12, pp. 2349–2365, Dec. 2017. PDF (33 MB) Low-res PDF (1.3 MB) Video (YouTube) External Project Page BibTeX DOI

Acknowledgments

This work was funded by the German Research Foundation (DFG) as part of the research training group GRK 1564 Imaging New Modalities, and by the UK Engineering and Physical Sciences Research Council (grant EP/K023578/1).