Beyond Convolution: A Taxonomy of Structured Operators for Learning-Based Image Processing

ArXi:2603.12067v1 Announce Type: cross The convolution operator is the fundamental building block of modern convolutional neural networks (CNNs), owing to its simplicity, translational equivariance, and efficient implementation. However, its structure as a fixed, linear, locally-averaging operator limits its ability to capture structured signal properties such as low-rank decompositions, adaptive basis representations, and non-uniform spatial dependencies.