OctMesh：一种用于无损三角网格压缩的统一八叉树层次框架
OctMesh: A Unified Octree-Hierarchical Framework for Lossless Triangle Mesh Compression
浏览论文内容
中文总结 AI 辅助
OctMesh提出统一八叉树层次框架，通过四类边分组与神经预测实现无损三角网格压缩，在MPEG V-DMC序列上平均7.033比特/面，较V-Mesh降低12.8%，并支持九级渐进细化。
中文摘要 AI 辅助
无损三角网格压缩必须同时保留顶点位置和连接性。八叉树支持学习式点云几何编码和渐进细化，但将其扩展到网格需要一种兼容的连接性表示。与体素的八种占用决策不同，父边可以发展出多种子连接，使得边细化难以用紧凑的预测先验进行建模。我们提出OctMesh，一种在共享八叉树层次上对几何和连接性进行编码的学习框架。其关键观察是，八叉树池化产生的父节点要么有一个子节点，要么有2到8个子节点。子边随后根据其端点父节点的类型以及端点是否共享父节点进行分组。每个候选组包含来自仅一个父节点或两个相连父节点的子节点。由此产生的四个类别定义了小的、固定形状的预测任务：由父图唯一确定的连接无需比特即可继承，而三个神经预测器估计剩余候选者的概率。这些概率指导实际边符号的算术编码。父内连接的二值化预测为预测不同父节点之间的连接提供上下文。一种图感知的父特征提取器结合了局部几何、父连接性和全局形状。连接性模型在粗层级使用专用权重，在细层级共享权重。残差边和最细层级的面选择载荷完成重建。在来自八个MPEG V-DMC测试序列的256帧上，OctMesh以平均每面7.033比特（比V-Mesh低12.8%）无损恢复最细层级的顶点坐标、边和无向面集合。相同的层次表示支持九级渐进顶点和边细化。
英文摘要
Lossless triangle mesh compression must preserve both vertex positions and connectivity. Octrees support learned point cloud geometry coding and progressive refinement, but extending them to meshes requires a compatible connectivity representation. Unlike the eight occupancy decisions of a voxel, a parent edge can develop into varied child connections, making edge refinement difficult to model with a compact prediction prior. We propose OctMesh, a learned framework that codes geometry and connectivity on a shared octree hierarchy. Its key observation is that octree pooling produces parents with either one child or two to eight children. Child edges are then grouped by their endpoint parents' types and whether the endpoints share a parent. Each candidate group contains children from just one parent or two connected parents. The resulting four categories define small, fixed-shape prediction tasks: connections uniquely determined by the parent graph are inherited without bits, while three neural predictors estimate probabilities for the remaining candidates. These probabilities guide arithmetic coding of the actual edge symbols. Binarized predictions of within-parent connections provide context for predicting connections between different parents. A graph-aware parent feature extractor combines local geometry, parent connectivity and global shape. The connectivity models use dedicated weights at coarse levels and share weights at fine levels. Residual edges and a finest-level face-selection payload complete the reconstruction. On 256 frames from eight MPEG V-DMC test sequences, OctMesh losslessly recovers the finest-level vertex-coordinate, edge and unoriented face sets at an average of 7.033 bits per face, 12.8% below V-Mesh. The same hierarchical representation supports nine levels of progressive vertex-and-edge refinement.
发表机构
- City University of Hong Kong（香港城市大学）
机构由 AI 辅助整理，请以论文原文为准。
