Efficient feature-preserving local projection operator for geometry reconstruction

• We present a feature-preserving locally optimal projection for static model.
• We present a spatio-temporal locally optimal projection for time-varying surfaces.
• We accelerate the projection operator using the random sampling technique.

This paper proposes an efficient and Feature-preserving Locally Optimal Projection operator (FLOP) for geometry reconstruction. Our operator is bilateral weighted, taking both spatial and geometric feature information into consideration for feature-preserving approximation. We then present an accelerated FLOP operator based on the random sampling of the Kernel Density Estimate (KDE), which produces reconstruction results close to those generated using the complete point set data, to within a given accuracy. Additionally, we extend our approach to time-varying data reconstruction, called the Spatial–Temporal Locally Optimal Projection operator (STLOP), which efficiently generates temporally coherent and stable feature-preserving results. The experimental results show that the proposed algorithms are efficient and robust for feature-preserving geometry reconstruction on both static models and time-varying data sets.