Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces ResPCC, an innovative neural point cloud codec specifically designed to withstand data loss during transmission, a common issue in real-world applications. By employing a Condition-Adaptive Latent Modulation (CALM) module and a Spatial-Channel Interleaving (SCI) mechanism at the encoder, along with a Mask-Aware Graph-based Latent Restoration (MGLR) module and Dictionary-based Refinement (DBR) stage at the decoder, the framework adapts to varying packet loss conditions. Evaluations demonstrate that ResPCC achieves superior stability and rate-distortion performance, maintaining high reconstruction fidelity even under significant packet loss rates of 5% to 30%.
ResPCC maintains high-quality 3D data transmission even in the face of severe packet loss, outperforming existing codecs in stability and reconstruction fidelity.
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.