Restoration of depth and intensity images using a graph laplacian regularization.
Abderrahim HalimiPeter ConnollyXiming RenYoann AltmannIstván GyöngyRobert K. HendersonStephen McLaughlinGerald S. BullerPublished in: CAMSAP (2017)
Keyphrases
- graph laplacian
- intensity images
- random walk
- spectral clustering
- shape from shading
- range images
- kernel machines
- euclidean space
- range data
- basis functions
- weighted graph
- surface normals
- manifold structure
- image restoration
- semi supervised learning
- color information
- low frequency
- image processing
- active contour model
- reproducing kernel hilbert space
- transfer function
- image segmentation
- pairwise
- training set
- photometric stereo
- multiscale
- low dimensional
- single image