scispace - formally typeset
Search or ask a question
Topic

Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.


Papers
More filters
Journal ArticleDOI
Xiankai Lu1, Yiyou Guo1, Na Liu1, Lihong Wan1, Tao Fang1 
TL;DR: The proposed NCJBU can well handle the edge inconsistency by making use of the property of both the guidance color image and the depth map, and a data driven scheme to properly determine the parameter in the model such that fine details and sharp depth edges are well preserved even for a large upsampling factor.
Abstract: Blurring depth edges and texture copy artifacts are challenging issues for guided depth map upsampling. They are caused by the inconsistency between depth edges and corresponding color edges. In this paper, we extend the well-known Joint Bilateral Upsampling (JBU) (Kopf et al. 2007) with a novel non-convex optimization framework for guided depth map upsampling, which is denoted as Non-Convex JBU (NCJBU). We show that the proposed NCJBU can well handle the edge inconsistency by making use of the property of both the guidance color image and the depth map. Through comprehensive experiments, we show that our NCJBU can preserve sharp depth edges and properly suppress texture copy artifacts. In addition, we present a data driven scheme to properly determine the parameter in our model such that fine details and sharp depth edges are well preserved even for a large upsampling factor (e.g., 8 ×). Experimental results on both simulated and real data show the effectiveness of our method.

13 citations

Proceedings ArticleDOI
01 Nov 2010
TL;DR: It is concluded that for cardiac images where motion of the organ plays an important role the prior alignment of the image data sets is a limiting factor for successfully applying an SRR.
Abstract: In cardiac imaging quantitative analysis heavily depends on the quality of the available image data. Cardiac MRI provides highly anisotropic voxel data. By combining multiple orthogonal data sets, isotropic volume data can be reconstructed. In this paper we investigate the increase in image quality by the use of a super-resolution reconstruction (SRR) algorithm. In particular, we compare a simple averaging with an SRR for combining two and three orthogonal views, respectively. We show that SRR outperforms averaging in case of the combination of two views, but that in case of three views SRR has no additional benefit compared to averaging. We conclude that for cardiac images where motion of the organ plays an important role the prior alignment of the image data sets is a limiting factor for successfully applying an SRR.

13 citations

Journal ArticleDOI
Daoyu Lin1, Guangluan Xu1, Wenjia Xu1, Yang Wang1, Xian Sun1, Kun Fu1 
TL;DR: A recursive efficient deep convolutional network for fast and accurate single-image SR with only 0.28M parameters is proposed and two-level recursive learning is proposed which can improve accuracy by increasing depth without adding any weight parameters.

13 citations

Journal ArticleDOI
TL;DR: Zhang et al. as discussed by the authors proposed a parallel network for multi-scale attention decoding for colorectal polyp segmentation, where a parallel attention module as well as a reverse fusion module are used to refine the edge information and improve the accuracy of the segmentation.

13 citations

Journal ArticleDOI
TL;DR: The work presented here is an extension of some of results to the case where the upsampling and downsampling ratios are not integers but rational numbers, hence, the name fractional biorthogonal partners.
Abstract: The concept of biorthogonal partners has been introduced recently by the authors. The work presented here is an extension of some of these results to the case where the upsampling and downsampling ratios are not integers but rational numbers, hence, the name fractional biorthogonal partners. The conditions for the existence of stable and of finite impulse response (FIR) fractional biorthogonal partners are derived. It is also shown that the FIR solutions (when they exist) are not unique. This property is further explored in one of the applications of fractional biorthogonal partners, namely, the fractionally spaced equalization in digital communications. The goal is to construct zero-forcing equalizers (ZFEs) that also combat the channel noise. The performance of these equalizers is assessed through computer simulations. Another application considered is the all-FIR interpolation technique with the minimum amount of oversampling required in the input signal. We also consider the extension of the least squares approximation problem to the setting of fractional biorthogonal partners.

13 citations


Network Information
Related Topics (5)
Convolutional neural network
74.7K papers, 2M citations
90% related
Image segmentation
79.6K papers, 1.8M citations
90% related
Feature extraction
111.8K papers, 2.1M citations
89% related
Deep learning
79.8K papers, 2.1M citations
88% related
Feature (computer vision)
128.2K papers, 1.7M citations
87% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023469
2022859
2021330
2020322
2019298
2018236