Improved gradient descent-based chroma subsampling method for color images in VVC

Abstract: Prior to encoding color images for RGB full-color, Bayer color filter array (CFA), and digital time delay integration (DTDI) CFA images, performing chroma subsampling on their converted chroma images is necessary and important. In this paper, we propose an effective general gradient descent-based chroma subsampling method for the above three kinds of color images, achieving substantial quality and quality-bitrate tradeoff improvement of the reconstructed color images when compared with the related methods. First, a bilinear interpolation based 2$\times$2 $t$ ($\in {RGB, Bayer, DTDI}$) color block-distortion function is proposed at the server side, and then in real domain, we prove that our general 2$\times$2 $t$ color block-distortion function is a convex function. Furthermore, a general closed form is derived to determine the initially subsampled chroma pair for each 2$\times$2 chroma block. Finally, an effective iterative method is developed to improve the initially subsampled $(U, V)$-pair. Based on the Kodak and IMAX datasets, the comprehensive experimental results demonstrated that on the newly released versatile video coding (VVC) platform VTM-8.0, for the above three kinds of color images, our chroma subsampling method clearly outperforms the existing chroma subsampling methods.