In colaboration with V-SENSE, and co-authored by Matt Moynihan, our founder Rafael Pagés and Aljosa Smolic, our paper on ‘A Self-regulating Spatio-Temporal Filter for Volumetric Video Point Clouds’ is one of the 25 select papers featured in the book ‘Computer Vision, Imaging and Computer Graphics Theory and Applications’.

Submitted to the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, this paper presents a self-regulating filter that can perform accurate and temporally coherent upsampling of dynamic point cloud data sequences. The system performs well in any environment, like dynamic real world scenarios with stationary/non-stationary cameras or even synthetically rendered environments.

We would like to thank Science Foundation Ireland for financial support and NVIDIA Corporation for donating the Titan Xp GPU, without which the research would not have been possible!