SyncAI.news, a Varaisys broadcasting
Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds
MY

Manlin Yao, Jiabin Liu, Guan Wang, Haixu Liu, Hui Li

· 1 min read

ResearcharXiv cs.CV

Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds

arXiv:2609.32789v1 Announce Type: new Abstract: Large-scale point cloud representations of complex geome tries incur prohibitive computational and memory costs, necessitating compressed implicit representations. To ad dress this, we propose a unified framework comprising im plicit geometric field representation, hierarchical frequency domain compression, and conditional high-frequency predic tion. Specifically, an unordered point cloud is mapped to an implicit field defined within its physical bounding box. A smooth Fourier pyramid is then constructed, where com pact low-frequency components capture the global geometry. Inter-scale high-frequency residuals are encoded to preserve the spatial information required for reconstructing fine geo metric details. To restore the high-frequency information lost during compression, we develop a hierarchical 3D neural net work. The reconstructed implicit field is converted back into a point cloud through isosurface extraction. Experiments on a complex-boundary point cloud with more than eight mil lion points demonstrate that the proposed method achieves a higher compression ratio than existing point cloud compres sion methods while maintaining comparable reconstruction quality.

Original source

This story was published by arXiv cs.CV and written by Manlin Yao, Jiabin Liu, Guan Wang, Haixu Liu, Hui Li. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News