Search

Image inpainting has achieved remarkable advancement in improving image quality via reconstructing the corrupted area with perceptual rationality. However, when the key semantic features of the mask area are blurred, existing methods solely relying on the corrupted image surrounding information may not be sufficient to restore the precise semantics of the original image. To solve this problem, in this letter, we propose a dual codec network guided by reference images, which obtains the effective semantic priors to reconstruct the lost detail feature of the corrupted image. Our network first aligns the reference image using a SIFT aligned module, then, extracts the texture feature and the gradient detail through a Fourier texture restoration module and an auxiliary feature extraction module, respectively, which finally emerge for image inpainting. To validate our scheme, we introduce the Reimage3K dataset with more realistic and diverse scenarios than existing datasets. Comprehensive experiments show that our scheme outperforms SOTA on PSNR, FID, and LPIPS by 3.29 dB, 54.5%, and 51.3% on DPED10K and 3.74 dB, 48.4%, 55.8% on Reimag3 k, respectively.

In this article, an iterative indirect Kalman filter is proposed to realize motion estimation based on inertial sensors. In the fusion of gyroscope, accelerometer, and magnetometer measurements, it is vital to decrease the impact of linear acceleration (LA) and external magnetic disturbances (EMAs) on the estimates. To this end, the proposed filter in this article performs first-order Gauss–Markov modeling for LA and EMA, respectively. Instead of simply adjusting the measurement noise covariance online, an iterative measurement strategy is presented to separate external disturbances based on the a posteriori estimation of the state during the measurement update. Moreover, a long short-term memory (LSTM) network is designed to assist the filter in the disturbance estimation process. It matches the process noise covariance to the strength of perturbation and adapts to the disturbance noise covariance. The experimental outcomes indicate that the proposed algorithm provides better accuracy and adaptive ability than some state-of-the-art results.

Cellulose-based flexible sensors, characterized by outstanding biocompatibility, degradability, and rich surface chemistry, offer considerable promise for human health monitoring. Limited extensibility, however, predisposes these materials to mechanical damage like cracking, which compromises sensor stability. Integrating self-healing functionalities not only restores their mechanical and sensory performances but also prolongs their service life. This paper reviews the diverse self-healing mechanisms of cellulose-based sensors and examines the contributions of dynamic bonding to reconciling self-healing prerequisites, efficiency, and mechanical integrity. The discussion extends to the latest advancements in cellulose-based flexible self-healing sensors for tracking health indicators, including movement, body temperature, sweat, and respiration, while also contemplating their prospects and emerging challenges.

A national cross-sectional study was performed to investigate the severity of burnout and its associated factors among doctors and nurses in ICUs in mainland China.

The interfacial strength and electrochemical performance of composite structural battery can be simultaneously enhanced by employing modified carbon fibers (MCFs) as electrode. In this study, an electrochemical-mechanical coupled modeling framework is developed to clarify the multiphysics nature of composite structural battery and guide their further optimal design. Effects of the thickness ratio of cathode to anode, electrode thickness and the volume ratio of modified layer on CFs for the electrochemical and mechanical properties are investigated. An optimal thickness ratio of MCFs cathode to anode exists for better electrochemical performance, while thinner MCFs electrode will trigger greater specific capacity. In addition, the volume fraction of carbon fiber in composites and that of modified layer on CF respectively dominate longitudinal modulus and electrochemical capacity.

Traditionally, transition metal oxides (TMOs)-based electrodes suffer from remarkable volume expansion and high risk of electrode pulverization during lithium intercalation and extraction. To tackle this issue, various structures have been incorporated into electrode structural design of TMOs. Herein, through the in-situ growth of cobalt-based metal organic frameworks (MOFs) and subsequent calcination at various temperatures, MOF-derived Co3O4nanosheets of three distinct structures are obtained on carbon cloth. Through investigation into the effect of temperature on microstructure and microstructure-electrochemical property relationship, the carbon cloth based Co3O4nanosheets electrode obtained at 500 °C is found out to demonstrate the highest lithium storage capabilities due to embedded porous structures and ultrafine crystallite sizes of Co3O4. This work presents an effective approach to optimize electrochemical properties, which is based on the temperature-induced electrode design. The findings in this study can be translated to the design of other high-area-capacity CC-based electrode for use in lithium ion batteries.