Point clouds (PC) are essential for AR/VR and autonomous driving but challenge compression schemes with their size, irregular sampling, and sparsity. MPEG's Geometry-based Point Cloud Compression (GPCC) methods successfully reduce bitrate; however, they introduce significant blocky artifacts in the reconstructed point cloud. We introduce a novel multi-scale postprocessing framework that fuses graph-Fourier latent attribute representations with sparse convolutions and channel-wise attention to efficiently deblock reconstructed point clouds. Against the GPCC TMC13v14 baseline, our approach achieves BD-rate reduction of 18.81\% in the Y channel and 18.14\% in the joint YUV on the 8iVFBv2 dataset, delivering markedly improved visual fidelity with minimal overhead.
Cite
@article{arxiv.2511.05047,
title = {J-SGFT: Joint Spatial and Graph Fourier Domain Learning for Point Cloud Attribute Deblocking},
author = {Muhammad Talha and Qi Yang and Zhu Li and Anique Akhtar and Geert Van Der Auwera},
journal= {arXiv preprint arXiv:2511.05047},
year = {2025}
}
Comments
Accepted to ICIP 2025 Workshop on Generative AI for World Simulations and Communications & Celebrating 40 Years of Excellence in Education: Honoring Professor Aggelos Katsaggelos, Sept. 2025, Alaska