perler/ppsurf

---
language:
- en
task_categories:
- summarization
tags:
- 3d meshes
- point clouds
- synthetic
- realistic
- CAD
- statues
pretty_name: Points2Surf Dataset
size_categories:
- 1K<n<10K
---

We introduced this dataset in Points2Surf, a method that turns point clouds into meshes.

It consists of objects from the [_ABC Dataset_](https://paperswithcode.com/dataset/abc-dataset-1), a collection of _Famous_ meshes and objects from [_Thingi10k_](https://paperswithcode.com/dataset/thingi10k).
These are mostly single objects per file, sometimes a couple of disconnected objects. Objects from the _ABC Dataset_ are CAD-models, the others are mostly statues with organic structures.

We created realistic point clouds using a simulated time-of-flight sensor from [_BlenSor_](https://www.blensor.org/). The point clouds have typical artifacts like noise and scan shadows.

Finally, we created training data consisting of randomly sampled query points with their ground-truth signed distance. The query points are 50% uniformly distributed in the unit cube and 50% near the surface with some random offset.

The training set consists of 4950 _ABC_ objects with varying number of scans and noise strength.
The validation sets are the same as the test set.
The _ABC_ test sets contain 100 objects, _Famous_ 22 and _Thingi10k_ 100. The test set variants are as follows:
(1) _ABC_ var (like training set), no noise, strong noise;
(2) _Famous_ no noise, medium noise, strong noise, sparse, dense scans;
(3) _Thingi10k_ no noise, medium noise, strong noise, sparse, dense scans

原始信息汇总

Points2Surf 数据集概述

基本信息

• 语言: 英语
• 任务类别: 摘要生成
• 标签: 3D网格, 点云, 合成, 真实感, CAD, 雕像
• 数据集名称: Points2Surf 数据集
• 数据规模: 1K<n<10K

数据集组成

• 来源: 包含来自ABC Dataset和Thingi10k的对象。
• 对象类型: 主要是单个对象文件，有时包含几个不相连的对象。ABC Dataset中的对象是CAD模型，其他主要是具有有机结构的雕像。

数据生成

• 点云生成: 使用BlenSor模拟的时间飞行传感器创建真实感点云，包含噪声和扫描阴影等典型特征。
• 训练数据: 包含随机采样的查询点及其真实距离值。查询点50%均匀分布在单位立方体中，50%在表面附近带有随机偏移。

数据集划分

• 训练集: 包含4950个ABC对象，具有不同数量的扫描和噪声强度。
• 验证集: 与测试集相同。
• 测试集:
  • ABC测试集包含100个对象。
  • Famous测试集包含22个对象。
  • Thingi10k测试集包含100个对象。
  • 测试集变体包括不同噪声强度（无噪声、中等噪声、强噪声）和扫描密度（稀疏、密集）。