Multivariate Fields of Experts
By: Stanislas Ducotterd, Michael Unser
Potential Business Impact:
Improves blurry pictures and scans faster.
We introduce the multivariate fields of experts, a new framework for the learning of image priors. Our model generalizes existing fields of experts methods by incorporating multivariate potential functions constructed via Moreau envelopes of the $\ell_\infty$-norm. We demonstrate the effectiveness of our proposal across a range of inverse problems that include image denoising, deblurring, compressed-sensing magnetic-resonance imaging, and computed tomography. The proposed approach outperforms comparable univariate models and achieves performance close to that of deep-learning-based regularizers while being significantly faster, requiring fewer parameters, and being trained on substantially fewer data. In addition, our model retains a relatively high level of interpretability due to its structured design.
Similar Papers
A Single-Parameter Factor-Graph Image Prior
Image and Video Processing
Cleans up blurry pictures automatically.
Improving Large Vision-Language Models' Understanding for Field Data
CV and Pattern Recognition
Helps computers understand science pictures and data.
Taming Flow-based I2V Models for Creative Video Editing
CV and Pattern Recognition
Edits videos like photos, easily and fast.