Topic
Bicubic interpolation
About: Bicubic interpolation is a research topic. Over the lifetime, 3348 publications have been published within this topic receiving 73126 citations.
Papers published on a yearly basis
Papers
More filters
••
01 Oct 2019TL;DR: The proposed KMSR consists of two stages: a pool of realistic blur-kernels with a generative adversarial network (GAN) and then a super-resolution network with HR and corresponding LR images constructed with the generated kernels that incorporates blur-kernel modeling in the training.
Abstract: Deep convolutional neural networks (CNNs), trained on corresponding pairs of high- and low-resolution images, achieve state-of-the-art performance in single-image super-resolution and surpass previous signal-processing based approaches. However, their performance is limited when applied to real photographs. The reason lies in their training data: low-resolution (LR) images are obtained by bicubic interpolation of the corresponding high-resolution (HR) images. The applied convolution kernel significantly differs from real-world camera-blur. Consequently, while current CNNs well super-resolve bicubic-downsampled LR images, they often fail on camera-captured LR images. To improve generalization and robustness of deep super-resolution CNNs on real photographs, we present a kernel modeling super-resolution network (KMSR) that incorporates blur-kernel modeling in the training. Our proposed KMSR consists of two stages: we first build a pool of realistic blur-kernels with a generative adversarial network (GAN) and then we train a super-resolution network with HR and corresponding LR images constructed with the generated kernels. Our extensive experimental validations demonstrate the effectiveness of our single-image super-resolution approach on photographs with unknown blur-kernels.
129 citations
••
TL;DR: The experimental results show that the extension method based on shape functions is the most accurate and the overall best spatio-temporal interpolation method.
128 citations
••
TL;DR: This paper presents the nearest neighbor value (NNV) algorithm for high resolution (H.R.) image interpolation, which selects one pixel, among four directly surrounding the empty location, whose value is almost equal to the value generated by the conventional bilinear interpolation algorithm.
Abstract: This paper presents the nearest neighbor value (NNV) algorithm for high resolution (H.R.) image interpolation. The difference between the proposed algorithm and conventional nearest neighbor algorithm is that the concept applied, to estimate the missing pixel value, is guided by the nearest value rather than the distance. In other words, the proposed concept selects one pixel, among four directly surrounding the empty location, whose value is almost equal to the value generated by the conventional bilinear interpolation algorithm. The proposed method demonstrated higher performances in terms of H.R. when compared to the conventional interpolation algorithms mentioned.
125 citations
••
TL;DR: Experimental results show that the subjective quality of the interpolated images is substantially improved by using the proposed algorithm compared with that of using conventional interpolation algorithms.
124 citations