运动重建
运动重建 (SfM) 是基于一组从不同视角拍摄的二维图像估计场景的三维结构的过程。Computer Vision Toolbox™ 提供端到端的 SfM 流程，包括特征检测、匹配、相机位姿估计、三角剖分和光束法平差。这些功能对于三维地图构建、摄影测量和自主导航等应用至关重要。
有关增量式运动重建流程的分步综合演练，请参阅多视图运动重建示例系列。该示例系列展示了如何使用特征袋方法从相机视图创建视图图、使用几何约束优化视图图、通过选择稳健的初始视图对来初始化三维重建，以及如何整合其余相机视图来重建完整的三维场景。有关如何使用场景的稀疏三维点云生成稠密三维网格的信息，请参阅Dense 3-D Reconstruction of Asteroid Surface from Image Sequence示例。
对于稠密重建和新视图合成，工具箱支持神经辐射场 (NeRF)。使用 trainNerfacto 函数在您的图像集合上训练 NeRF 模型并生成新视图。然后，您可以使用 pc2surfacemesh (Lidar Toolbox) 函数使用点云生成三维网格。
函数
主题
增量式运动重建
- 多视图运动重建
利用增量式运动重建方法，根据一组二维视图推断场景的三维结构。 (自 R2026a 起)
基础知识
- What Is Structure from Motion?
Estimate three-dimensional structures from two-dimensional image sequences. - 坐标系
指定像素索引、空间坐标和三维坐标系。 - Point Feature Types
Choose functions that return and accept points objects for several types of features. - Local Feature Detection and Extraction
Learn the benefits and applications of local feature detection and extraction.
精选示例
多视图运动重建
利用增量式运动重建方法，根据一组二维视图推断场景的三维结构。
Dense 3-D Reconstruction from Multiple Views Using RAFT Optical Flow
Reconstruct dense 3-D scene by augmenting sparse Structure-from-Motion (SfM) point cloud with dense pixel correspondences estimated using RAFT optical flow.
Dense 3-D Reconstruction from Two Views Using RAFT Optical Flow
Perform dense 3-D scene reconstruction from two monocular images showing different viewpoints using RAFT optical flow model.
Dense 3-D Reconstruction of Asteroid Surface from Image Sequence
Reconstruct dense 3-D point cloud and continuous surface mesh for an asteroid using 2-D images.
Create View Graph Using Bag of Features
Extract features from images and build a view graph based on visual similarity using bag-of-features approach.
Refine View Graph Using Geometric Verification
Refine the view graph created purely based on visual similarity by verifying geometric consistency between image pairs.
Reconstruct 3-D Scene from Geometrically Refined Pair of Initial Views
Initialize 3-D reconstruction by selecting a robust image pair from the geometrically refined view graph.
Reconstruct Complete 3-D Scene Using Incremental Structure from Motion
Use incremental structure from motion to generate complete 3-D scene by integrating all camera views with the initialized 3-D reconstruction.
基于两个视图的运动重建
根据一组二维图像推断场景的三维结构。
Reconstruct 3-D Scenes and Synthesize Novel Views Using Neural Radiance Field Model
Reconstruct 3-D scenes and synthesize novel views from a set of 2-D images using the Nerfacto Neural Radiance Field (NeRF) model.
