Incorporating non-motion cues into 3D motion segmentation

Amit Gruber*, Yair Weiss

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


We address the problem of segmenting an image sequence into rigidly moving 3D objects. An elegant solution to this problem in the case of orthographic projection is the multibody factorization approach in which the measurement matrix is factored into lower rank matrices. Despite progress in factorization algorithms, their performance is still far from satisfactory and in scenes with missing data and noise, most existing algorithms fail. In this paper we propose a method for incorporating 2D non-motion cues (such as spatial coherence) into multibody factorization. We show the similarity of the problem to constrained factor analysis and use the EM algorithm to find the segmentation. We show that adding these cues improves performance in real and synthetic sequences.

Original languageAmerican English
Pages (from-to)261-271
Number of pages11
JournalComputer Vision and Image Understanding
Issue number3
StatePublished - Dec 2007


  • 3D motion segmentation
  • Constrained factorization
  • EM algorithm
  • Factor analysis
  • Graphical models
  • Multibody factorization
  • Spatial coherence
  • Structure from motion


Dive into the research topics of 'Incorporating non-motion cues into 3D motion segmentation'. Together they form a unique fingerprint.

Cite this