In this study, the authors propose an approach towards dense depth reconstruction, combining robust feature-based structure from motion with the spatial coherence of dense reconstruction algorithms. To achieve this, a variational framework was set up, minimising the epipolar reprojection error and the image brightness constraint, while preserving discontinuities in the depth field by introducing an anisotropic diffusion term. As initial guess for the iterative solver, a region growing algorithm is proposed which mixes sparse and dense data
De Cubber, G & Sahli, H 2012, 'Partial differential equation-based dense 3D structure and motion estimation from monocular image sequences', IET Computer Vision, vol. 6, no. 3, pp. 174-185.
De Cubber, G., & Sahli, H. (2012). Partial differential equation-based dense 3D structure and motion estimation from monocular image sequences. IET Computer Vision, 6(3), 174-185.
@article{60609b4949cb4dd1aaff4745c602c1f3,
title = "Partial differential equation-based dense 3D structure and motion estimation from monocular image sequences",
abstract = "In this study, the authors propose an approach towards dense depth reconstruction, combining robust feature-based structure from motion with the spatial coherence of dense reconstruction algorithms. To achieve this, a variational framework was set up, minimising the epipolar reprojection error and the image brightness constraint, while preserving discontinuities in the depth field by introducing an anisotropic diffusion term. As initial guess for the iterative solver, a region growing algorithm is proposed which mixes sparse and dense data",
keywords = "computer vision, 3d recosntruction, stereo, optical flow",
author = "{De Cubber}, Geert and Hichem Sahli",
year = "2012",
language = "English",
volume = "6",
pages = "174--185",
journal = "IET Computer Vision",
issn = "1751-9632",
publisher = "Institution of Engineering and Technology",
number = "3",
}