Collaborative Total Variation: A General Framework for Vectorial TV Models

August 06, 2015 Β· Declared Dead Β· πŸ› SIAM Journal of Imaging Sciences

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers arXiv ID 1508.01308 Category cs.CV: Computer Vision Cross-listed math.HO, math.NA, math.OC Citations 81 Venue SIAM Journal of Imaging Sciences Last Checked 5 months ago
Abstract
Even after over two decades, the total variation (TV) remains one of the most popular regularizations for image processing problems and has sparked a tremendous amount of research, particularly to move from scalar to vector-valued functions. In this paper, we consider the gradient of a color image as a three dimensional matrix or tensor with dimensions corresponding to the spatial extend, the differences to other pixels, and the spectral channels. The smoothness of this tensor is then measured by taking different norms along the different dimensions. Depending on the type of these norms one obtains very different properties of the regularization, leading to novel models for color images. We call this class of regularizations collaborative total variation (CTV). On the theoretical side, we characterize the dual norm, the subdifferential and the proximal mapping of the proposed regularizers. We further prove, with the help of the generalized concept of singular vectors, that an $\ell^{\infty}$ channel coupling makes the most prior assumptions and has the greatest potential to reduce color artifacts. Our practical contributions consist of an extensive experimental section where we compare the performance of a large number of collaborative TV methods for inverse problems like denoising, deblurring and inpainting.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago

Died the same way β€” πŸ‘» Ghosted