SHREC'16 Partial Benchmark (SHREC 2016 TRACK: PARTIAL MATCHING OF DEFORMABLE SHAPES)

找到两个形状之间的对应关系是计算机图形和几何处理中的一项基本任务，应用范围从纹理映射到动画。一个特别具有挑战性和广泛研究的环境是当形状被允许进行准等距变形时，就像我们考虑不同姿势的关节体时发生的那样。一个更有趣的场景是部分对应，其中仅显示形状的子集，并且必须将其与其可变形版本匹配。部分对应问题出现在许多涉及通过 3D 传感器获取真实数据的应用中，这不可避免地导致由于遮挡和部分视图而丢失部分。我们提出了一个基准来评估算法在存在不同数量和种类的偏性的情况下建立完整形状与其变形版本之间的对应关系的性能。

Establishing correspondences between two shapes is a fundamental task in computer graphics and geometric processing, with applications ranging from texture mapping to animation. A particularly challenging and widely studied scenario is when shapes are allowed to undergo quasi-isometric deformations, as occurs when considering articulated bodies in different poses. A more intriguing scenario is partial correspondence, where only a subset of a shape is presented and must be matched to its deformable counterpart. The partial correspondence problem arises in numerous applications involving real-world data acquired via 3D sensors, which inevitably leads to missing parts due to occlusions and partial views. We present a benchmark for evaluating the performance of algorithms in establishing correspondences between a full shape and its deformable variants under varying amounts and types of partiality.

搜集汇总

背景与挑战

背景概述

该数据集是SHREC 2016竞赛中用于评估可变形形状部分匹配算法的基准。它针对计算机图形学中因遮挡或部分视图导致形状数据缺失的挑战性场景，旨在测试算法在不同程度缺失下建立完整形状与变形部分之间对应关系的性能。