KPPF: Keypoint-Based Point-Pair-Feature for Scalable Automatic Global Registration of Large RGB-D Scans

Lucas Malleus, Thomas Fisichella, Diane Lingrand, Frederic Precioso, Nicolas Gros, Yann Noutary, Luc Robert, Lirone Samoun; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2495-2502

One of the most important challenges in the field of 3D data processing is to be able to reconstruct a complete 3D scene with a high accuracy from several captures. In this article we propose an automatic scalable global registration method under the following constraints: markerless, very large scale data (several, potentially many millions of points per scans), little overlap between scans, for more than two or three dozens of scans, without a priori knowledge on the 6 degrees of freedom. We evaluate thoroughly our method on our own dataset of 33 real large scale scans of an indoor building. The data presents some pairs of scans with very little overlap, architectural challenges, several millions of points per scan. We will make this dataset public as part of a benchmark available for the community. We have thus evaluated the accuracy of our method, the scalability to the initial amount of points and the robustness to occlusions, little scan overlap and architectural challenges.