Discontinuities have been important in visual reconstruction to avoid oversmoothing. The article raises the question as to whether location of discontinuities is necessary in this process. The author proposes a class of adaptive regularizers (ARs) for reconstruction in the framework of regularization, in an attempt to solve the conflict between 'oversmoothing across discontinuities' and 'finding discontinuities'. The proposal differs from existing methods in the way it controls continuity, in which true discontinuities are considered in the mathematical sense only. A simple analog neuron-like circuit for hardware implementation is suggested. Experimental results are presented.
展开▼