Convolutional Sparse Coding: Boundary Handling Revisited
This work solves a specific technical issue in image processing for researchers and practitioners, but it is incremental as it builds on prior boundary handling methods.
The paper addresses boundary artifacts in convolutional sparse coding by showing that existing spatial mask methods can fail under certain conditions, proposing a solution, and demonstrating its effectiveness in an image deblurring problem.
Two different approaches have recently been proposed for boundary handling in convolutional sparse representations, avoiding potential boundary artifacts arising from the circular boundary conditions implied by the use of frequency domain solution methods by introducing a spatial mask into the convolutional sparse coding problem. In the present paper we show that, under certain circumstances, these methods fail in their design goal of avoiding boundary artifacts. The reasons for this failure are discussed, a solution is proposed, and the practical implications are illustrated in an image deblurring problem.