Autors: Bozhilov, I. B., Tonchev K., Manolova, A. H., Petkova, R. R.
Title: 3D Human Body Models Compression and Decompression Algorithm Based on Graph Convolutional Networks for Holographic communication
Keywords: 3D human body models , Holographic communication , Graph con

Abstract: People are used to perceiving the world around them in the form of three-dimensional objects. Therefore, a logical step in the development of communication technologies is to move to the implementation of communication systems in a three-dimensional environment. Such communication is holographic communication. In holographic communication between people, three-dimensional models of the participants' bodies are transmitted. The shape of the human body is highly variable because it depends on factors such as age, gender, ethnicity, health status, etc. Also, the body deforms significantly when taking different positions. All these factors must be taken into account when developing compression algorithms so that the maximum amount of information can be preserved. The aim of this paper is to present an algorithm for compression and decompression of 3D models of a human body in a static pose, based on graph convolutional neural networks.

References

    Issue

    25th International Symposium on Wireless Personal Multimedia Communications (WPMC), pp. 532-537, 2022, Denmark, IEEE, DOI 10.1109/WPMC55625.2022.10014791

    Copyright IEEE

    Цитирания (Citation/s):
    1. Xia, G., Ye, W., Xue, P., Sun, Y., & Liu, Q. (2023). Motion Compression using Structurally Connected Neural Network. IEEE Transactions on Circuits and Systems for Video Technology. - 2023 - в издания, индексирани в Scopus или Web of Science

    Вид: публикация в международен форум, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus и Web of Science