PROJECT TITLE :

Compressive Bilateral Filtering - 2015

ABSTRACT:

This paper presents an efficient constant-time bilateral filter that produces a close to-optimal performance tradeoff between approximate accuracy and computational complexity while not any complicated parameter adjustment, known as a compressive bilateral filter (CBLF). The constant-time means that that the computational complexity is independent of its filter window size. Although many existing constant-time bilateral filters are proposed step-by-step to pursue a additional efficient performance tradeoff, they have less centered on the optimal tradeoff for his or her own frameworks. It is necessary to discuss this question, because it can reveal whether or not a continuing-time algorithm still has lots area for enhancements of performance tradeoff. This paper tackles the question from a viewpoint of compressibility and highlights the fact that state-of-the-art algorithms have not however touched the optimal tradeoff. The CBLF achieves a near-optimal performance tradeoff by 2 key ideas: one) an approximate Gaussian range kernel through Fourier analysis and a couple of) a amount length optimization. Experiments demonstrate that the CBLF considerably outperforms state-of-the-art algorithms in terms of approximate accuracy, computational complexity, and usefulness.