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.
|Number of pages||8|
|Publication status||Published - 30 Jun 2013|
|Event||IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) - Oregon, US, UK United Kingdom|
Duration: 25 Jun 2013 → 27 Jun 2013
|Conference||IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)|
|Country||UK United Kingdom|
|Period||25/06/13 → 27/06/13|