Summary. In this paper we introduce a new robust framework suitable for the task of finding correspondences in computer vision. This task lies in the heart of many problems like stereovision, 3D model reconstruction, image stitching, camera autocalibration, recognition and image retrieval and a host of others. If the problem domain is general enough, the correspondence problem can seldom employ any well-structured prior knowledge. This leads to tasks that have to find maximum cardinality solutions satisfying some weak optimality condition and a set of constraints. To avoid artifacts, robustness is required to cope with decision under occlusion, uncertainty or insufficiency of data and local violations of prior model. The proposed framework is based on a robust modification of graph-theoretic notion known as digraph kernel.