IEEE Trans Image Process. 2015 Dec;24(12):4943-51. doi: 10.1109/TIP.2015.2472294. Epub 2015 Aug 24.
We propose a 2D non-separable block-lifting structure (2D-NSBL) that is easily formulated from the 1D separable block-lifting structure (1D-SBL) and 2D non-separable lifting structure (2D-NSL). The 2D-NSBL can be regarded as an extension of the 2D-NSL, because a two-channel 2D-NSBL is completely equivalent to a 2D-NSL. We apply the 2D-NSBL to M-channel ( M=2(n), n ∈ N) perfect reconstruction filter banks (PRFBs). The 2D-NSBL-based PRFBs outperform 1D-SBL-based PRFBs at lossy-to-lossless coding, whose image quality is scalable from lossless data to high compressed lossy data, because their rounding errors are reduced by merging many rounding operations.
我们提出了一种二维非可分离块提升结构（2D-NSBL），它可以从一维可分离块提升结构（1D-SBL）和二维非可分离提升结构（2D-NSL）轻松构建。2D-NSBL 可以看作是 2D-NSL 的扩展，因为双通道 2D-NSBL 与 2D-NSL 完全等效。我们将 2D-NSBL 应用于 M 通道（M=2(n)，n ∈ N）的完美重构滤波器组（PRFB）。在有损到无损编码方面，基于 2D-NSBL 的 PRFB 优于基于 1D-SBL 的 PRFB，因为它们的舍入误差通过合并许多舍入操作而减少。其图像质量可以从无损数据扩展到高压缩有损数据，
