Related Experiment Video
Updated: Jul 6, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures
Published on: November 14, 2019
Nonrigid structure-from-motion: estimating shape and motion with hierarchical Priors
Lorenzo Torresani1, Aaron Hertzmann, Chris Bregler
1Microsoft Research, Cambridge, CB3 0FB, UK. ltorre@microsoft.com
This study introduces a novel method to reconstruct non-rigid 3D object shape and motion from 2D video. The approach uses Probabilistic Principal Components Analysis (PPCA) for robustly handling missing data and modeling temporal dynamics.
Area of Science:
- Computer Vision
- 3D Reconstruction
- Non-rigid Object Analysis
Background:
- Recovering 3D shape and motion from uncalibrated 2D data is challenging.
- Modeling non-rigid deformations requires robust assumptions and techniques.
Purpose of the Study:
- To develop a method for estimating time-varying 3D shape and motion of non-rigid objects from uncalibrated 2D point tracks.
- To create a robust system capable of handling missing data and modeling temporal dynamics in object shape.
Main Methods:
- Utilizing a Probabilistic Principal Components Analysis (PPCA) shape model.
- Developing an estimation algorithm that simultaneously reconstructs 3D shape and motion.
- Incorporating temporal dynamics modeling for enhanced robustness.
Main Results:
- Successful recovery of time-varying shape and motion from 2D point tracks.
- Robust handling of missing data points through PPCA and temporal modeling.
- Accurate estimation of facial deformation models from video.
Conclusions:
- The proposed PPCA-based method effectively reconstructs non-rigid 3D object dynamics.
- The approach offers robustness against missing data and models temporal shape variations.
- This technique advances the field of 3D reconstruction from uncalibrated video sources.
Related Concept Videos
Planar Rigid-Body Motion
Planar motion is typically divided into three distinct categories. The first is rectilinear translation, demonstrated by a subway train that moves along...
Curvilinear Motion: Rectangular Components
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the time...
Relative Motion Analysis using Rotating Axes
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it instrumental in...
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
Structural Classification of Joints
A fibrous joint is where the adjacent bones are united by fibrous connective...
Kinematic Equations for Rotation
For instance, imagine a point A on a rigid body engaged in circular motion. The translational velocity of this particular point can be calculated by taking the time derivatives of the displacement equation, which essentially measures the...