Dynamic SfM: Detecting Scene Changes from Image Pairs

Simple item page
dc.contributor.authorWang, Tuanfeng Y.en_US
dc.contributor.authorKohli, Pushmeeten_US
dc.contributor.authorMitra, Niloy J.en_US
dc.contributor.editorMirela Ben-Chen and Ligang Liuen_US
dc.date.accessioned2015-07-06T05:01:04Z
dc.date.available2015-07-06T05:01:04Z
dc.date.issued2015en_US
dc.description.abstractDetecting 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.en_US
dc.description.number5en_US
dc.description.sectionheadersGeometry and Imagesen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume34en_US
dc.identifier.doi10.1111/cgf.12706en_US
dc.identifier.pages177-189en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12706en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleDynamic SfM: Detecting Scene Changes from Image Pairsen_US
Files
Collections
34-Issue 5
SGP15: Eurographics Symposium on Geometry Processing (CGF 34-5)