SAFT: Sensitivity-Aware Filtering and Transmission for Adaptive 3D Point Cloud Communication over Wireless Channels

TL;DR

SAFT is a novel learned framework for adaptive 3D point cloud transmission over wireless channels, improving robustness and fidelity especially in low-SNR conditions.

Contribution

It introduces a sensitivity-guided token filtering module and a training-only symbol-usage penalty for stable, adaptive point cloud transmission.

Findings

SAFT outperforms traditional source-channel coding pipelines in geometric fidelity.

SAFT shows significant gains in low-SNR regimes, indicating enhanced robustness.

Experiments on ShapeNet, ModelNet40, and 8iVFB validate the effectiveness of SAFT.

Abstract

Reliable transmission of 3D point clouds over wireless channels is challenging due to time-varying signal-to-noise ratio (SNR) and limited bandwidth. This paper introduces sensitivity-aware filtering and transmission (SAFT), a learned transmission framework that integrates a Point-BERT-inspired encoder, a sensitivity-guided token filtering (STF) unit, a quantization block, and an SNR-aware decoder for adaptive reconstruction. Specifically, the STF module assigns token-wise importance scores based on the reconstruction sensitivity of each token under channel perturbation. We further employ a training-only symbol-usage penalty to stabilize the discrete representation, without affecting the transmitted payload. Experiments on ShapeNet, ModelNet40, and 8iVFB show that SAFT improves geometric fidelity (D1/D2 PSNR) compared with a separate source--channel coding pipeline (G-PCC combined with LDPC and QAM) and existing learned baselines, with the largest gains observed in low-SNR regimes, highlighting improved robustness under limited bandwidth.