DeepRAHT用学习方法实现点云属性压缩，端到端高效且可控制失真。
DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression
- 基于稀疏张量的端到端框架，自动学习区域自适应分层变换
- 预测性变换降低码率，实验显示比基线更快更鲁棒
- 支持可变码率编码，适合实时点云压缩应用
区域自适应分层变换（RAHT）是一种高效的点云属性压缩（PCAC）方法，但在深度学习中的应用仍不充分。本文提出一种基于稀疏张量的端到端损失性PCAC框架DeepRAHT，将RAHT变换嵌入学习重建过程，无需手动预处理。引入预测性RAHT以降低码率，并设计基于学习的预测模型提升性能。此外，提出一种运行长度编码驱动的码率代理，实现无缝可变码率编码并增强鲁棒性。DeepRAHT为可逆且失真可控的框架，确保其下界性能，具备显著应用潜力。实验表明，该方法在性能、速度与鲁棒性上均优于基线方法。
原文摘要 · Abstract (English)
Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT transform is performed within the learning reconstruction process, without requiring manual RAHT for preprocessing. We also introduce the predictive RAHT to reduce bitrates and design a learning-based prediction model to enhance performance. Moreover, we devise a bitrate proxy that applies run-length coding to entropy model, achieving seamless variable-rate coding and improving robustness. DeepRAHT is a reversible and distortion-controllable framework, ensuring its lower bound performance and offering significant application potential. The experiments demonstrate that DeepRAHT is a high-performance, faster, and more robust solution than the baseline methods. Project Page: https://github.com/zb12138/DeepRAHT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。