ResPCC: A Loss-Resilient Neural Point Cloud Codec over Lossy Networks

2026-08-12

AI Summary

This work addresses the severe degradation in feature fidelity and geometric quality experienced by existing learning-based point cloud compression methods under lossy network conditions due to packet loss. To this end, we propose the first end-to-end neural codec framework with intrinsic robustness to packet loss, which adaptively adjusts its encoding strategy based on perceived packet loss rates and recovers corrupted features at the decoder. The core innovations include Conditional Adaptive Latent Modulation (CALM), Spatial-Channel Interleaving (SCI), Mask-aware Graph-based Latent Recovery (MGLR), and Dictionary-Based Refinement (DBR). Evaluated on ShapeNet and SemanticKITTI under packet loss rates ranging from 5% to 30%, our method significantly outperforms current baselines, achieving state-of-the-art performance in both reconstruction fidelity and rate-distortion efficiency.

Abstract

Point cloud compression (PCC) is critical for efficient storage and transmission of 3D data. While recent learning-based PCC methods achieve good rate-distortion (R-D) performance, they generally rely on ideal transmission conditions. In practice, packet loss is a common issue and can severely distort latent features, causing coordinate drift and geometric degradation. To address this challenge, we present ResPCC, the first end-to-end neural point cloud codec designed to offer intrinsic resilience against data loss. Our framework is loss-rate-aware and adapts to diverse packet loss conditions. At the encoder, we introduce a Condition-Adaptive Latent Modulation (CALM) module to adjust latent feature distributions according to the perceived loss rate, as well as a Spatial-Channel Interleaving (SCI) mechanism that transforms channel-wise data extinction into spatially scattered element-wise missing patterns. At the decoder, we develop a Mask-Aware Graph-based Latent Restoration (MGLR) module, followed by a Dictionary-based Refinement (DBR) stage to recover corrupted features and align them with canonical priors. Evaluations on ShapeNet and SemanticKITTI under 5\% to 30\% packet loss rates show that ResPCC consistently delivers superior stability and R-D performance over baselines. Our framework maintains high reconstruction fidelity under lossy conditions, providing a reliable solution for 3D data transmission over practical networks. Code is available at https://github.com/starrynight314/ResPCC.

Problem

• Point Cloud Compression
• Packet Loss
• Lossy Networks
• Latent Feature Distortion
• Geometric Degradation

Innovation

• loss-resilient
• neural point cloud compression
• latent modulation
• graph-based restoration
• packet loss adaptation