Dynamic SfM: Detecting Scene Changes from Image Pairs

Tuanfeng Y. Wang, Pushmeet Kohli, Niloy Mitra

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

Detecting changes in scenes is important in many scene understanding tasks. In this paper, we pursue this goal simply from a pair of image recordings. Specifically, our goal is to infer what the objects are, how they are structured, and how they moved between the images. The problem is challenging as large changes make point-level correspondence establishment difficult, which in turn breaks the assumptions of standard Structure-from-Motion (SfM). We propose a novel algorithm for dynamic SfM wherein we first generate a pool of potential corresponding points by hypothesizing over possible movements, and then use a continuous optimization formulation to obtain a low complexity solution that best explains the scene recordings, i.e.; the input image pairs. We test the algorithm on a variety of examples to recover the multiple object structures and their changes.

Original languageEnglish (US)
Pages (from-to)177-189
Number of pages13
JournalComputer Graphics Forum
Volume34
Issue number5
DOIs
StatePublished - Aug 1 2015

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Dynamic SfM: Detecting Scene Changes from Image Pairs'. Together they form a unique fingerprint.

Cite this