Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chang, Junlin, Han, Yubo, Yue, Hang, Thompson, John S, Liu, Rongke
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.03819
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908859832991744
author Chang, Junlin
Han, Yubo
Yue, Hang
Thompson, John S
Liu, Rongke
author_facet Chang, Junlin
Han, Yubo
Yue, Hang
Thompson, John S
Liu, Rongke
contents The widespread adoption of depth sensors has substantially lowered the barrier to point-cloud acquisition. This letter proposes a semantic wireless transmission framework for three dimension (3D) point clouds built on Deep Joint Source - Channel Coding (DeepJSCC). Instead of sending raw features, the transmitter predicts combination weights over a receiver-side semantic orthogonal feature pool, enabling compact representations and robust reconstruction. A folding-based decoder deforms a 2D grid into 3D, enforcing manifold continuity while preserving geometric fidelity. Trained with Chamfer Distance (CD) and an orthogonality regularizer, the system is evaluated on ModelNet40 across varying Signal-to-Noise Ratios (SNRs) and bandwidths. Results show performance on par with SEmantic Point cloud Transmission (SEPT) at high bandwidth and clear gains in bandwidth-constrained regimes, with consistent improvements in both Peak Signal-to-Noise Ratio (PSNR) and CD. Ablation experiments confirm the benefits of orthogonalization and the folding prior.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transmit Weights, Not Features: Orthogonal-Basis Aided Wireless Point-Cloud Transmission
Chang, Junlin
Han, Yubo
Yue, Hang
Thompson, John S
Liu, Rongke
Machine Learning
The widespread adoption of depth sensors has substantially lowered the barrier to point-cloud acquisition. This letter proposes a semantic wireless transmission framework for three dimension (3D) point clouds built on Deep Joint Source - Channel Coding (DeepJSCC). Instead of sending raw features, the transmitter predicts combination weights over a receiver-side semantic orthogonal feature pool, enabling compact representations and robust reconstruction. A folding-based decoder deforms a 2D grid into 3D, enforcing manifold continuity while preserving geometric fidelity. Trained with Chamfer Distance (CD) and an orthogonality regularizer, the system is evaluated on ModelNet40 across varying Signal-to-Noise Ratios (SNRs) and bandwidths. Results show performance on par with SEmantic Point cloud Transmission (SEPT) at high bandwidth and clear gains in bandwidth-constrained regimes, with consistent improvements in both Peak Signal-to-Noise Ratio (PSNR) and CD. Ablation experiments confirm the benefits of orthogonalization and the folding prior.
title Transmit Weights, Not Features: Orthogonal-Basis Aided Wireless Point-Cloud Transmission
topic Machine Learning
url https://arxiv.org/abs/2512.03819