Optical flow estimation using Laplacian Mesh Energy

Wenbin Li, Darren Cosker, Matthew Brown, Rui Tang

Research output: Contribution to conferencePaper

16 Citations (Scopus)

Abstract

In this paper we present a novel non-rigid optical flow algorithm for dense image correspondence and non-rigid registration. The algorithm uses a unique Laplacian Mesh Energy term to encourage local smoothness whilst simultaneously preserving non-rigid deformation. Laplacian deformation approaches have become popular in graphics research as they enable mesh deformations to preserve local surface shape. In this work we propose a novel Laplacian Mesh Energy formula to ensure such sensible local deformations between image pairs. We express this wholly within the optical flow optimization, and show its application in a novel coarse-to-fine pyramidal approach. Our algorithm achieves the state-of-the-art performance in all trials on the Garg et al. dataset, and top tier performance on the Middlebury evaluation.
Original languageEnglish
Pages2435-2442
Number of pages8
DOIs
Publication statusPublished - 30 Jun 2013
EventIEEE International Conference on Computer Vision and Pattern Recognition (CVPR) - Oregon, US, UK United Kingdom
Duration: 25 Jun 201327 Jun 2013

Conference

ConferenceIEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
CountryUK United Kingdom
CityOregon, US
Period25/06/1327/06/13

    Fingerprint

Cite this

Li, W., Cosker, D., Brown, M., & Tang, R. (2013). Optical flow estimation using Laplacian Mesh Energy. 2435-2442. Paper presented at IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Oregon, US, UK United Kingdom. https://doi.org/10.1109/CVPR.2013.315