Multiregression spatially variant blur kernel estimation based on inter‐kernel consistency

Abstract

Most single‐image super‐resolution (SR) models suffer from the degradation of image restoration performance when restoring a high‐resolution (HR) image from a low‐resolution (LR) image downscaled using an unknown blur kernel. The spatially invariant blur kernel estimators have been proposed to predict the blur kernel to address this issue. Nevertheless, the spatially variant blur exists in the real‐world; thus, these blur kernel estimators are unsuitable for real‐world applications. Although the spatially variant blur kernel estimators have been proposed, SR models still suffer from performance degradation because these estimators do neither consider the consistency between surrounding blur kernels nor refine non‐parametric blur kernels as parameters. To address this problem, the authors propose a multiregression spatially variant blur kernel estimation based on inter‐kernel consistency. The proposed estimator consists of three parts: non‐parametric regression, an inter‐kernel consistency block, and parametric regression. Specifically, it predicts spatially variant blur kernels while considering the inter‐kernel consistency between nearby blur kernels. Our source codes with pretrained models are available on https://github.com/alsgur0720/multiregression.

Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution

“…The SISR technique [11][12][13][14][15] is well known in computer vision and aims to generate an HR image from a single LR counterpart. Early deep learning models, such as the SR convolutional neural network (SRCNN) [16] and fast SR CNN [17], use shallow architectures to learn mappings from LR to HR images.…”