arXiv subjects

Xi Cheng

Publications and source records attributed to Xi Cheng.

44 records · Page 3Linked to original sources

arXiv2020

Oxygen Evolution Reaction on Perovskites: A Multieffect Descriptor Study Combining Experimental and Theoretical Methods

The correlation between ex situ electronic conductivity, oxygen vacancy content, flat-band potential (Efb), and the oxygen evolution reaction (OER) activity for a wide range of perovskite compositions are investigated experimentally and theoretically. It is found that all of these parameters can affect the OER activity; however, none of them alone play a crucial role in determining the electrocatalytic activity. The correlation of one single physicochemical property with the OER activity always presents deviation points, indicating that a limitation does exist for such 2-dimensional correlations. Nevertheless, these deviations can be explained considering other physicochemical properties and their correlation with the OER activity. Hence, this work aims in simultaneously linking the OER activity with several physicochemical materials properties. The concept of the OER/multidescriptor relationship represents a significant advancement in the search and design of highly active oxygen evolution catalysts, in the quest for efficient anodes in water electrolyzers.

cond-mat.mtrl-sci↗

arXiv2020

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

cs.CV↗

arXiv2019

AIM 2019 Challenge on Image Demoireing: Methods and Results

This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. This paper describes the challenge, and focuses on the proposed solutions and their results. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. A new dataset, called LCDMoire was created for this challenge, and consists of 10,200 synthetically generated image pairs (moire and clean ground truth). The challenge was divided into 2 tracks. Track 1 targeted fidelity, measuring the ability of demoire methods to obtain a moire-free image compared with the ground truth, while Track 2 examined the perceptual quality of demoire methods. The tracks had 60 and 39 registered participants, respectively. A total of eight teams competed in the final testing phase. The entries span the current the state-of-the-art in the image demoireing problem.

eess.IV↗

arXiv2019

The solid-state Li-ion conductor Li$_7$TaO$_6$: A combined computational and experimental study

We study the oxo-hexametallate Li$_7$TaO$_6$ with first-principles and classical molecular dynamics simulations, obtaining a low activation barrier for diffusion of $\sim$0.29 eV and a high ionic conductivity of $5.7 \times 10^{-4}$ S cm$^{-1}$ at room temperature (300 K). We find evidence for a wide electrochemical stability window from both calculations and experiments, suggesting its viable use as a solid-state electrolyte in next-generation solid-state Li-ion batteries. To assess its applicability in an electrochemical energy storage system, we performed electrochemical impedance spectroscopy measurements on multicrystalline pellets, finding substantial ionic conductivity, if below the values predicted from simulation. We further elucidate the relationship between synthesis conditions and the observed ionic conductivity using X-ray diffraction, inductively coupled plasma optical emission spectrometry, and X-ray photoelectron spectroscopy, and study the effects of Zr and Mo doping.

cond-mat.mtrl-sci↗

arXiv2019

Multi-scale Dynamic Feature Encoding Network for Image Demoireing

The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textures, which deteriorates the quality of photos. Moire spreads across various frequency bands of images and is a dynamic texture with varying colors and shapes, which pose two main challenges in demoireing---an important task in image restoration. In this paper, towards addressing the first challenge, we design a multi-scale network to process images at different spatial resolutions, obtaining features in different frequency bands, and thus our method can jointly remove moire in different frequency bands. Towards solving the second challenge, we propose a dynamic feature encoding module (DFE), embedded in each scale, for dynamic texture. Moire pattern can be eliminated more effectively via DFE.Our proposed method, termed Multi-scale convolutional network with Dynamic feature encoding for image DeMoireing (MDDM), can outperform the state of the arts in fidelity as well as perceptual on benchmarks.

cs.CV↗

arXiv2019

Polynomial Regression As an Alternative to Neural Nets

Despite the success of neural networks (NNs), there is still a concern among many over their "black box" nature. Why do they work? Here we present a simple analytic argument that NNs are in fact essentially polynomial regression models. This view will have various implications for NNs, e.g. providing an explanation for why convergence problems arise in NNs, and it gives rough guidance on avoiding overfitting. In addition, we use this phenomenon to predict and confirm a multicollinearity property of NNs not previously reported in the literature. Most importantly, given this loose correspondence, one may choose to routinely use polynomial models instead of NNs, thus avoiding some major problems of the latter, such as having to set many tuning parameters and dealing with convergence issues. We present a number of empirical results; in each case, the accuracy of the polynomial approach matches or exceeds that of NN approaches. A many-featured, open-source software package, polyreg, is available.

cs.LG↗

arXiv2018

Triple Attention Mixed Link Network for Single Image Super Resolution

Single image super resolution is of great importance as a low-level computer vision task. Recent approaches with deep convolutional neural networks have achieved im-pressive performance. However, existing architectures have limitations due to the less sophisticated structure along with less strong representational power. In this work, to significantly enhance the feature representation, we proposed Triple Attention mixed link Network (TAN) which consists of 1) three different aspects (i.e., kernel, spatial and channel) of attention mechanisms and 2) fu-sion of both powerful residual and dense connections (i.e., mixed link). Specifically, the network with multi kernel learns multi hierarchical representations under different receptive fields. The output features are recalibrated by the effective kernel and channel attentions and feed into next layer partly residual and partly dense, which filters the information and enable the network to learn more powerful representations. The features finally pass through the spatial attention in the reconstruction network which generates a fusion of local and global information, let the network restore more details and improves the quality of reconstructed images. Thanks to the diverse feature recalibrations and the advanced information flow topology, our proposed model is strong enough to per-form against the state-of-the-art methods on the bench-mark evaluations.

cs.CV↗

arXiv2018

SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks

Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it has brought a huge amount of computation and memory consumption. In this work, in order to make the super resolution models more effective, we proposed a novel single image super resolution method via recursive squeeze and excitation networks (SESR). By introducing the squeeze and excitation module, our SESR can model the interdependencies and relationships between channels and that makes our model more efficiency. In addition, the recursive structure and progressive reconstruction method in our model minimized the layers and parameters and enabled SESR to simultaneously train multi-scale super resolution in a single model. After evaluating on four benchmark test sets, our model is proved to be above the state-of-the-art methods in terms of speed and accuracy.

cs.CV↗