用多段视频自动重建日常物体完整网格，无需扫描仪
NeuralMeshing: Complete Object Mesh Extraction from Casual Captures
- 通过多视频+已知点定位，用运动恢复结构法对齐帧
- 融合多视角结果生成无缺失的完整三维网格
- 适合无专业设备但需快速建模的用户
如何在无法使用商业3D扫描仪的情况下，从日常拍摄的视频中提取物体的完整几何模型？本文提出一种自动化系统，可从两段或更多视频中生成物体的几何模型。系统只需在每段视频至少一帧中标记一个已知点，可通过棋盘格或AR标记自动识别。其余帧通过运动恢复结构（Structure-from-Motion）技术自动定位到世界坐标空间。利用多视频数据并融合结果，可生成无孔洞的完整物体网格，避免依赖复杂的补洞算法。系统代码已开源：https://github.com/FlorisE/NeuralMeshing。
原文摘要 · Abstract (English)
How can we extract complete geometric models of objects that we encounter in our daily life, without having access to commercial 3D scanners? In this paper we present an automated system for generating geometric models of objects from two or more videos. Our system requires the specification of one known point in at least one frame of each video, which can be automatically determined using a fiducial marker such as a checkerboard or Augmented Reality (AR) marker. The remaining frames are automatically positioned in world space by using Structure-from-Motion techniques. By using multiple videos and merging results, a complete object mesh can be generated, without having to rely on hole filling. Code for our system is available from https://github.com/FlorisE/NeuralMeshing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。