ProDAT: Progressive Density-Aware Tail-Drop for Point Cloud Coding

2025-10-19

AI Summary

To address the lack of progressive decoding capability in point cloud geometry coding, this paper proposes the first learning-based method enabling adaptive progressive decoding with a single model. The core innovation is a density-aware tail feature dropping mechanism: a density estimation module quantifies local point cloud density to dynamically rank the importance of latent features, followed by tunable feature pruning for hierarchical reconstruction across multiple bitrates. Unlike prior approaches, our method requires no multi-model switching or additional parameters, significantly enhancing coding flexibility and deployment efficiency. Extensive experiments on SemanticKITTI and ShapeNet demonstrate state-of-the-art performance, achieving BD-rate gains of 28.6% and 18.15% in PSNR-D2, respectively, outperforming existing learning-based geometric coders.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Three-dimensional (3D) point clouds are becoming increasingly vital in applications such as autonomous driving, augmented reality, and immersive communication, demanding real-time processing and low latency. However, their large data volumes and bandwidth constraints hinder the deployment of high-quality services in resource-limited environments. Progres- sive coding, which allows for decoding at varying levels of detail, provides an alternative by allowing initial partial decoding with subsequent refinement. Although recent learning-based point cloud geometry coding methods have achieved notable success, their fixed latent representation does not support progressive decoding. To bridge this gap, we propose ProDAT, a novel density-aware tail-drop mechanism for progressive point cloud coding. By leveraging density information as a guidance signal, latent features and coordinates are decoded adaptively based on their significance, therefore achieving progressive decoding at multiple bitrates using one single model. Experimental results on benchmark datasets show that the proposed ProDAT not only enables progressive coding but also achieves superior coding efficiency compared to state-of-the-art learning-based coding techniques, with over 28.6% BD-rate improvement for PSNR- D2 on SemanticKITTI and over 18.15% for ShapeNet

Problem

• Enables progressive decoding for point cloud geometry
• Addresses bandwidth constraints in resource-limited environments
• Achieves multi-bitrate coding with single model efficiency

Innovation

• ProDAT uses density-aware tail-drop mechanism
• It enables progressive decoding with single model
• Achieves over 28.6% BD-rate improvement on datasets