Wang Jianqiang, Xue Ruixiang, Li Jiaxin, Ding Dandan, Lin Yi, Ma Zhan
IEEE Trans Pattern Anal Mach Intell. 2025 Jan;47(1):252-268. doi: 10.1109/TPAMI.2024.3462945. Epub 2024 Dec 4.
A universal multiscale conditional coding framework, Unicorn, is proposed to code the geometry and attribute of any given point cloud. Attribute compression is discussed in Part II of this paper, while geometry compression is given in Part I of this paper. We first construct the multiscale sparse tensors of each voxelized point cloud attribute frame. Since attribute components exhibit very different intrinsic characteristics from the geometry element, e.g., 8-bit RGB color versus 1-bit occupancy, we process the attribute residual between lower-scale reconstruction and current-scale data. Similarly, we leverage spatially lower-scale priors in the current frame and (previously processed) temporal reference frame to improve the probability estimation of attribute intensity through conditional residual prediction in lossless mode or enhance the attribute reconstruction through progressive residual refinement in lossy mode for better performance. The proposed Unicorn is a versatile, learning-based solution capable of compressing a great variety of static and dynamic point clouds in both lossy and lossless modes. Following the same evaluation criteria, Unicorn significantly outperforms standard-compliant approaches like MPEG G-PCC, V-PCC, and other learning-based solutions, yielding state-of-the-art compression efficiency with affordable encoding/decoding runtime.
提出了一种通用的多尺度条件编码框架Unicorn，用于对任何给定的点云的几何形状和属性进行编码。本文第二部分讨论属性压缩，而第一部分给出几何压缩。我们首先构建每个体素化点云属性帧的多尺度稀疏张量。由于属性分量与几何元素具有非常不同的内在特征，例如8位RGB颜色与1位占用情况，我们处理较低尺度重建与当前尺度数据之间的属性残差。同样，我们利用当前帧和（先前处理的）时间参考帧中的空间较低尺度先验，通过无损模式下的条件残差预测来提高属性强度的概率估计，或者通过有损模式下的渐进残差细化来增强属性重建，以获得更好的性能。所提出的Unicorn是一种通用的、基于学习的解决方案，能够在有损和无损模式下压缩各种静态和动态点云。按照相同的评估标准，Unicorn显著优于符合标准的方法，如MPEG G-PCC、V-PCC以及其他基于学习的解决方案，在可承受的编码/解码运行时间下产生了领先的压缩效率。
