Among all methods for reconstructing missing regions in a digital image, the so-called exemplar-based algorithms are very efficient and often produce striking results. They are based on the simple idea-initially used for texture synthesis-that the unknown part of an image can be reconstructed by simply pasting samples extracted from the known part. Beyond heuristic considerations, there have been very few contributions in the literature to explain from a mathematical point of view the performances of these purely algorithmic and discrete methods. More precisely, a recent paper by Levina and Bickel [64] provides a theoretical explanation of their ability to recover very well the texture, but nothing equivalent has been done so far for the recovery of geometry. Our purpose in this paper is twofold: 1. To propose well-posed variational models in the continuous domain that can be naturally associated to exemplar-based algorithms; 2. To investigate their ability to reconstruct either local or long-range geometric features like edges. In particular, we propose several optimization models in R N , we discuss their relation with the original algorithms, and show the existence of minimizers in the framework of functions of bounded variation. Focusing on a simple 2D situation, we provide experimental evidences that basic exemplar-based algorithms are able to reconstruct a local geometric information whereas the minimization of the proposed variational models allows a global reconstruction of geometry and in particular of smooth edges. The derivation of globally minimizing algorithms associated to these models is still an open problem. Yet the results presented in this paper are a first step towards new inpainting algorithms with an improved quality of geometry reconstruction and no loss of quality for texture reconstruction.
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects. We show on several databases that dropping the instance-level annotations only yields mild performance losses. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings. We believe that such a method is of great benefit for helping art historians to explore large digital databases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.