Bilateral filter has demonstrated its effectiveness in many traditional methods for image restoration tasks. In this letter, we incorporate the idea of bilateral grid processing a CNN framework and propose stereo super-resolution network (BSSRnet). Specifically, use parallax-attention module to information from left right views learn content-aware filters. Then, these filters are used recover m...

The efficient implementation of connected filters is an important issue in signal processing. A typical example is the cascade of two filters, e.g., an adaptive filter with a time-invariant prefilter. The filtering and adaptation is carried out very efficiently in the frequency domain whenever filters with many coefficients are required. This is implemented as a block algorithm by using overlap...

This paper presents an application of variable infinite impulse response (IIR) digital filters based on the Constantinides frequency transformation to adaptive filtering. We propose a new unified framework for adaptive detection of narrowband signals using variable band-stop IIR digital filters with arbitrary transfer functions. It is also shown that our proposed method includes the all-pass-ba...

Subband adaptive filters have been proposed to circumvent the drawbacks of slow convergence and high computational complexity associated with time domain adaptive filters. Subband processing introduces transmission delays and signal degradations due to aliasing effects. In order to overcome the transmission delays, delayless adaptive filtering has been introduced where the coefficient adaptatio...