A Perceptually Inspired Variational Framework for Color Enhancement
By: Rodrigo Palma-Amestoy , Edoardo Provenzi , Marcelo Bertalmío and more
Potential Business Impact:
Improves picture colors to look more natural.
Basic phenomenology of human color vision has been widely taken as an inspiration to devise explicit color correction algorithms. The behavior of these models in terms of significative image features (such as contrast and dispersion) can be difficult to characterize. To cope with this, we propose to use a variational formulation of color contrast enhancement that is inspired by the basic phenomenology of color perception. In particular, we devise a set of basic requirements to be fulfilled by an energy to be considered as `perceptually inspired', showing that there is an explicit class of functionals satisfying all of them. We single out three explicit functionals that we consider of basic interest, showing similarities and differences with existing models. The minima of such functionals is computed using a gradient descent approach. We also present a general methodology to reduce the computational cost of the algorithms under analysis from ${\cal O}(N^2)$ to ${\cal O}(N\log N)$, being $N$ the number of input pixels.
Similar Papers
Contrast Sensitivity Function of Multimodal Vision-Language Models
CV and Pattern Recognition
Tests how AI sees like humans.
Prompt-based Consistent Video Colorization
CV and Pattern Recognition
Makes old black and white movies colorful automatically.
Color and Frequency Correction for Image Colorization
CV and Pattern Recognition
Makes old photos look colorful and clear again.