A wavelet frame coefficient total variational model for image restoration
This work addresses image restoration for applications like photography or medical imaging, but it is incremental as it builds on existing total variation and wavelet methods.
The authors tackled image restoration by proposing a vector total variation model that applies different smoothing to features like edges and cartoons, enabling simultaneous edge preservation and noise removal. They proved solution existence, used the split Bregman algorithm for solving, and demonstrated advantages in quality and efficiency over related methods through experiments.
In this paper, we propose a vector total variation (VTV) of feature image model for image restoration. The VTV imposes different smoothing powers on different features (e.g. edges and cartoons) based on choosing various regularization parameters. Thus, the model can simultaneously preserve edges and remove noises. Next, the existence of solution for the model is proved and the split Bregman algorithm is used to solve the model. At last, we use the wavelet filter banks to explicitly define the feature operator and present some experimental results to show its advantage over the related methods in both quality and efficiency.