Topic
Image scaling
About: Image scaling is a research topic. Over the lifetime, 3541 publications have been published within this topic receiving 50108 citations. The topic is also known as: upscaling & downscaling.
Papers published on a yearly basis
Papers
More filters
01 Jul 2017
TL;DR: In this paper, a deep fully convolutional neural network is proposed to estimate a spatially-adaptive convolution kernel for each pixel, which captures both the local motion between the input frames and the coefficients for pixel synthesis.
Abstract: Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This paper presents a robust video frame interpolation method that combines these two steps into a single process. Specifically, our method considers pixel synthesis for the interpolated frame as local convolution over two input frames. The convolution kernel captures both the local motion between the input frames and the coefficients for pixel synthesis. Our method employs a deep fully convolutional neural network to estimate a spatially-adaptive convolution kernel for each pixel. This deep neural network can be directly trained end to end using widely available video data without any difficult-to-obtain ground-truth data like optical flow. Our experiments show that the formulation of video interpolation as a single convolution process allows our method to gracefully handle challenges like occlusion, blur, and abrupt brightness change and enables high-quality video frame interpolation.
289 citations
TL;DR: This paper presents an algorithm for electron tomographic reconstruction and sparse image interpolation that exploits the nonlocal redundancy in images, and demonstrates that the algorithm produces higher quality reconstructions on both simulated and real electron microscope data, along with improved convergence properties compared to other methods.
Abstract: Many material and biological samples in scientific imaging are characterized by nonlocal repeating structures. These are studied using scanning electron microscopy and electron tomography. Sparse sampling of individual pixels in a two-dimensional image acquisition geometry, or sparse sampling of projection images with large tilt increments in a tomography experiment, can enable high speed data acquisition and minimize sample damage caused by the electron beam. In this paper, we present an algorithm for electron tomographic reconstruction and sparse image interpolation that exploits the nonlocal redundancy in images. We adapt a framework, termed plug-and-play priors, to solve these imaging problems in a regularized inversion setting. The power of the plug-and-play approach is that it allows a wide array of modern denoising algorithms to be used as a “prior model” for tomography and image interpolation. We also present sufficient mathematical conditions that ensure convergence of the plug-and-play approach, and we use these insights to design a new nonlocal means denoising algorithm. Finally, we demonstrate that the algorithm produces higher quality reconstructions on both simulated and real electron microscope data, along with improved convergence properties compared to other methods.
267 citations
08 Sep 2018
TL;DR: In this article, an end-to-end deep learning codec is proposed for video compression, which is based on repeated image interpolation, and it outperforms H.264 and MPEG-4 Part 2.
Abstract: An ever increasing amount of our digital communication, media consumption, and content creation revolves around videos. We share, watch, and archive many aspects of our lives through them, all of which are powered by strong video compression. Traditional video compression is laboriously hand designed and hand optimized. This paper presents an alternative in an end-to-end deep learning codec. Our codec builds on one simple idea: Video compression is repeated image interpolation. It thus benefits from recent advances in deep image interpolation and generation. Our deep video codec outperforms today’s prevailing codecs, such as H.261, MPEG-4 Part 2, and performs on par with H.264.
252 citations
TL;DR: A new upsampling method is proposed to recover some of this high frequency information by using a data-adaptive patch-based reconstruction in combination with a subsampling coherence constraint to outperform classical interpolation methods in terms of quantitative measures and visual observation.
250 citations
TL;DR: A new satellite image resolution enhancement technique based on the interpolation of the high-frequency subbands obtained by discrete wavelet transform and the input image to achieve a sharper image is proposed.
Abstract: Satellite images are being used in many fields of research. One of the major issues of these types of images is their resolution. In this paper, we propose a new satellite image resolution enhancement technique based on the interpolation of the high-frequency subbands obtained by discrete wavelet transform (DWT) and the input image. The proposed resolution enhancement technique uses DWT to decompose the input image into different subbands. Then, the high-frequency subband images and the input low-resolution image have been interpolated, followed by combining all these images to generate a new resolution-enhanced image by using inverse DWT. In order to achieve a sharper image, an intermediate stage for estimating the high-frequency subbands has been proposed. The proposed technique has been tested on satellite benchmark images. The quantitative (peak signal-to-noise ratio and root mean square error) and visual results show the superiority of the proposed technique over the conventional and state-of-art image resolution enhancement techniques.
246 citations