A motion-texture aware denoising for economic hardware design

An economic motion and texture aware denosing framework is proposed to facilitate parallel hardware design. The denoising framework performs on a block basis and features a spatial and temporal predictor and then a linear denoising filter optimal in the Minimum Mean Square Error (MMSE) sense. We first analyze the texture and motion strength around the neighborhood of a noisy pixel and then produce an effective predictor to correlate with the pixel of interest. Both the predictor and the noisy pixel are input into the linear denoiser to finally remove the noise. This framework only refers the information of the neighborhood of a noisy pixel and explores the best spatial and temporal denoising ratio adaptive to its local characteristics. Experiments show that the proposed framework outperforms the traditional block based denoising method by 1-3 dB of PSNR in denoising quality and also achieves a 1-3 dB gain when using it in HEVC encoder.