{"ID":2844831,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05047","arxiv_id":"2511.05047","title":"J-SGFT: Joint Spatial and Graph Fourier Domain Learning for Point Cloud Attribute Deblocking","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.05047","url_pdf":"https://arxiv.org/pdf/2511.05047v1","authors":"[\"Muhammad Talha\",\"Qi Yang\",\"Zhu Li\",\"Anique Akhtar\",\"Geert Van Der Auwera\"]","published":"2025-11-07T07:36:26Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false}