Application of Heterogenous Motion Models towards Structure Recovery from Motion

  title={Application of Heterogenous Motion Models towards Structure Recovery from Motion},
  author={M. V. Rohith and C. Kambhamettu},
Non-rigid structure estimates are often performed under the assumption that linear combination of a few rigid basis shapes can describe the deformation. However, the quality of reconstruction suffers as the number of basis shapes increase. When a natural video (which may contain rigid, articulated and non-rigid objects together with camera motion) is to be processed, the complexity of motion precludes use of rigid SFM methods. We propose that this problem may be approached using the notions of… 
1 Citations
Robust bundle adjustment for large-scale structure from motion
A robust Bundle Adjustment (RBA) algorithm to optimize the initial 3D point-clouds and camera parameters which are produced by the Structure from Motion system and clearly outperforms the state-of-the-art methods on both computational cost and precision.


Estimation and utilization of articulations in recovering non-rigid structure from motion using motion subspaces
This work proposes a novel algorithm for segmenting motion to find articulated components and a hierarchical NRSFM algorithm which estimates articulated and non-rigid structure separately.
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
A reconstruction method using a Probabilistic Principal Components Analysis shape model and an estimation algorithm that simultaneously estimates 3D shape and motion for each instant, learns the PPCA model parameters, and robustly fills-in missing data points is proposed.
Articulated structure from motion by factorization
  • P. Tresadern, I. Reid
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
It is shown that articulation constraints can be imposed during factorization and self-calibration to recover consistent 3D structure and motion, from which link lengths and joint angles can be computed.
Factorization for non-rigid and articulated structure using metric projections
An alternating least-squares approach associated with a globally optimal projection step onto the manifold of metric constraints for recovering the 3D shape and motion of deformable and articulated objects purely from uncalibrated 2D image measurements is proposed.
Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors
This paper uses an automatic segmentation algorithm to identify the set of rigid points which in turn is used to estimate the internal camera calibration parameters and the overall rigid motion and formalises the problem of non-rigid shape estimation as a constrained non-linear minimization adding priors on the degree of deformability of each point.
Trajectory Space: A Dual Representation for Nonrigid Structure from Motion
A dual approach to describe the evolving 3D structure in trajectory space by a linear combination of basis trajectories is proposed and the Discrete Cosine Transform (DCT) is used as the object independent basis and it is demonstrated that it approaches Principal Component Analysis (PCA) for natural motions.
Automated articulated structure and 3D shape recovery from point correspondences
A set of point tracks are decompose into rigid-bodied overlapping regions which are associated with skeletal links, while joint centres can be derived from the regions of overlap, to formulate the problem of 3D reconstruction as one of model assignment, where each model corresponds to the motion and shape parameters of an articulated body part.
Multibody Structure-from-Motion in Practice
It is argued that all of these difficulties need to be handled online as structure-from-motion estimation progresses, and an exemplary solution using the framework of probabilistic model-scoring is presented.
Non-rigid structure from motion with complementary rank-3 spaces
This paper proposes a new algorithm that revises the standard matrix factorization approach in NR-SFM, providing improved results on high-frequency deformations of both articulated and simpler deformable shapes.
Recovering non-rigid 3D shape from image streams
This paper proposes a novel technique based on a non-rigid model, where the 3D shape in each frame is a linear combination of a set of basis shapes, and can be factored in a three-step process to yield pose, configuration and shape.