Sparse representations have recently drawn much attention from the signal processing and learning communities. The basic underlying model consist of considering that natural images, or signals in general, admit a sparse decomposition in some redundant dictionary. This means that we can find a linear combination of a few atoms from the dictionary that lead to an efficient representation of the original signal. Recent results have shown that learning overcomplete non-parametric dictionaries for image representations, instead of using off-the-shelf ones, significantly improves numerous image and video processing tasks. In this talk, I will first present our results on learning multiscale overcomplete dictionaries for color image and video restoration. I will present the framework and provide numerous examples showing state-of-the-art results. I will then briefly show how to extend this to image classification, deriving energies and optimization procedures that lead to learning non-parametric dictionaries for sparse representations optimized for classification. I will conclude by showing results on the extension of this to sensing and the learning of incoherent dictionaries. The work I present in this talk is the result of great collaborations with J. Mairal (ENS, Paris), F. Rodriguez (UofM/Spain), J. Martin-Duarte (UofM/Kodak), I. Ramirez (UofM), F. Lecumberry (UofM), F. Bach (ENS, Paris), M. Elad (Technion, Israel), J. Ponce (ENS, Paris), and A. Zisserman (ENS/Oxford).