Data for: ABC-Draco

ABC-Draco is a GLTF Draco conversion of the NYU ABC-Dataset. "Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows generating data in different formats and resolutions, enabling fair comparisons for a wide range of geometric learning algorithms." (Sebastian Koch et al. 2019) The collection contains 751,407 dense point clouds with normals; using lossy Draco compression, the total file size is approximately two orders of magnitude smaller than the original, which makes this version useful in more resource-constrained environments. License terms are identical to the original dataset.ABC-Draco 是 NYU ABC 数据集（NYU ABC-Dataset）的通用场景传输格式（GL Transmission Format，GLTF）Draco 压缩转换版本。“每个模型均由显式参数化曲线与曲面的集合构成，可为微分几何量、面片分割、几何特征检测以及形状重建任务提供真值基准。通过对曲面与曲线的参数化描述进行采样，可生成不同格式与分辨率的数据集，从而为各类几何学习算法提供公平的对比基础。”（Sebastian Koch 等，2019）该数据集集合包含751,407组携带法向量的密集点云；采用有损Draco压缩（Draco Compression）技术，总文件体积较原始数据集缩小约两个数量级，使得该版本可在资源受限的计算环境中得以应用。其授权条款与原始数据集完全一致。

搜集汇总

背景与挑战

背景概述

ABC-Draco是NYU ABC-Dataset的GLTF Draco压缩版本，包含751,407个带法线的密集点云，用于3D模型、计算机辅助设计和几何深度学习。该数据集通过有损Draco压缩技术，将文件大小减小约两个数量级，使其更适合资源受限的环境，同时保持与原始数据集相同的许可条款。