Skip to main content
Open Access Publications from the University of California


UCLA Electronic Theses and Dissertations bannerUCLA

Analysis by Synthesis: 3D Image Parsing Using Spatial Grammar and Markov Chain Monte Carlo

  • Author(s): Qi, Siyuan
  • Advisor(s): Zhu, Song-Chun
  • et al.

Scene understanding is a fundamental problem in computer vision research. We

address this problem in an “analysis by synthesis” fashion - explain observed data

(an 2D image) according to a set of spatial grammar (describes the underlying

functional arrangement and 3D geometric structure of a scene) that generate it.

The inference process is carried out in a Bayesian framework. The posterior

probability includes a prior probability reflecting the knowledge of indoor 3D scene

structure encoded by grammar, and a likelihood that evaluates the accuracy of the

re-projected image and the physical plausibility. The most reasonable explanation

of the image is given by a parse tree that maximizes the posterior probability, and

it is found by reversible-jump Markov Chain Monte Carlo sampling.

Main Content
Current View