Image upsampling via spatially adaptive block-matching filtering

In this paper we present a novel wavelet-domain image upsampling algorithm based on iterative spatially adaptive filtering. A high-resolution image is reconstructed by alternating two procedures: spatially adaptive filtering and projection on the observation-constrained subspace. The Block-Matching and 3D filtering (BM3D) [3] technique is used to suppress ringing, and reconstruct missing wavelet detail coefficients. The BM3D algorithm exploits the local image statistics collected from similar blocks to extract local and non-local image features by 3D transform-domain shrinkage. It results in high-quality upsampled images, with sharp edges and practically no artifacts.