Interpreting and Extending The Guided Filter Via Cyclic Coordinate Descent
This work provides a theoretical foundation for extending image filtering methods, which is incremental but offers practical improvements for computer vision applications.
The paper reveals that the Guided Filter can be interpreted as a Cyclic Coordinate Descent solver, enabling extensions by modifying its objective function and deriving new rolling filtering schemes, with experiments showing state-of-the-art results.
In this paper, we will disclose that the Guided Filter (GF) can be interpreted as the Cyclic Coordinate Descent (CCD) solver of a Least Square (LS) objective function. This discovery implies a possible way to extend GF because we can alter the objective function of GF and define new filters as the first pass iteration of the CCD solver of modified objective functions. Moreover, referring to the iterative minimizing procedure of CCD, we can derive new rolling filtering schemes. Hence, under the guidance of this discovery, we not only propose new GF-like filters adapting to the specific requirements of applications but also offer thoroughly explanations for two rolling filtering schemes of GF as well as the way to extend them. Experiments show that our new filters and extensions produce state-of-the-art results.