Vector-Valued Image Regularization with PDE's : A Common Framework for Different Applications

1 We address the problem of vector-valued image regularization with variational methods and PDE's. From the study of existing formalisms, we propose a unifying framework based on a very local interpretation of the regularization processes. The resulting equations are then specialized into new regularization PDE's and corresponding numerical schemes that respect the local geometry of vector-valued images. They are finally applied on a wide variety of image processing problems, including color image restoration, inpainting, magnification and flow visualization.

• Type: Conference
• Year: 2003
• Where: CVPR
• Authors: David Tschumperlé, Rachid Deriche
• Keywords: Color Image Restoration, Computer Vision, CVPR 2003, Image Processing Problems, Regularization Processes, Unifying Framework, Vector-valued Image Regularization