We propose a mixed-resolution point-cloud representation and an example-based super-resolution framework, from which several processing tools can be derived, such as compression, denoising and error concealment. By inferring the high-frequency content of low-resolution frames based on the similarities between adjacent full-resolution frames, the proposed framework achieves an average 1.18 dB gain over low-pass versions of the point-cloud, for a projection-based distortion metric[1-2].
@article{arxiv.1803.06466,
title = {Example-based super-resolution for point-cloud video},
author = {Diogo C. Garcia and Tiago A. Fonseca and Ricardo L. de Queiroz},
journal= {arXiv preprint arXiv:1803.06466},
year = {2018}
}
Comments
This paper was submitted to ICIP-2018 and its copyright may be transferred to IEEE. Work partially supported by CNPq under grant 308150/2014-7