Search

Single image super‐resolution (SISR) is a promising research direction in computer vision and image processing for improving the visual perception of low‐quality images. In recent years, deep learning algorithms have driven tremendous development in SR, and SR methods based on various network architectures have significantly improved the quality of reconstructed images. Although there has been a large amount of reviews focusing on SISR, few studies have focused specifically on network architectures for SISR. This paper aims to provide a systematic overview of the design ideas of SISR using multiple architectures, including Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Transformer, and Diffusion model. In addition, an experimental analysis and comparison of state‐of‐the‐art SR algorithms have been performed on publicly available quantitative and qualitative datasets. Finally, some future directions are discussed that may help other community researchers. [ABSTRACT FROM AUTHOR]

With the development of display technology, more displays can cover the wider gamut, but most of the content they show is based on a small gamut. It is significant to employ gamut expansion (GE) to expand the small gamut images to a wider target gamut. Most of the existing GE methods only use global or local operations to realize the mapping from small gamut to wide gamut. However, the utilization of both global information and local feature is important for GE. In this article, the authors propose a combined global‐local gamut expansion network (G‐LGENet) for mapping the input standard RGB (sRGB) images to wider ProPhoto RGB space. In G‐LGENet, the global colour mapping module first extracts and fuses the global colour priors and learns the mapping of colour information for the corresponding pixels. And then, the local enhancement (LE) is designed to extract the local colour information between the corresponding pixel and neighbourhood pixels. The experimental results on a sRGB‐to‐ProPhoto dataset have demonstrated that the proposed G‐LGENet outperforms the other excellent GE methods qualitatively and visually. [ABSTRACT FROM AUTHOR]

Background: Low‐dose computed tomography (LDCT) can reduce the dose of X‐ray radiation, making it increasingly significant for routine clinical diagnosis and treatment planning. However, the noise introduced by low‐dose X‐ray exposure degrades the quality of CT images, affecting the accuracy of clinical diagnosis. Purpose: The noises, artifacts, and high‐frequency components are similarly distributed in LDCT images. Transformer can capture global context information in an attentional manner to create distant dependencies on targets and extract more powerful features. In this paper, we reduce the impact of image errors on the ability to retain detailed information and improve the noise suppression performance by fully mining the distribution characteristics of image information. Methods: This paper proposed an LDCT noise and artifact suppressing network based on Swin Transformer. The network includes a noise extraction sub‐network and a noise removal sub‐network. The noise extraction and removal capability are improved using a coarse extraction network of high‐frequency features based on full convolution. The noise removal sub‐network improves the network's ability to extract relevant image features by using a Swin Transformer with a shift window as an encoder–decoder and skip connections for global feature fusion. Also, the perceptual field is extended by extracting multi‐scale features of the images to recover the spatial resolution of the feature maps. The network uses a loss constraint with a combination of L1 and MS‐SSIM to improve and ensure the stability and denoising effect of the network. Results: The denoising ability and clinical applicability of the methods were tested using clinical datasets. Compared with DnCNN, RED‐CNN, CBDNet and TSCN, the STEDNet method shows a better denoising effect on RMSE and PSNR. The STEDNet method effectively removes image noise and preserves the image structure to the maximum extent, making the reconstructed image closest to the NDCT image. The subjective and objective analysis of several sets of experiments shows that the method in this paper can effectively maintain the structure, edges, and textures of the denoised images while having good noise suppression performance. In the real data evaluation, the RMSE of this method is reduced by 18.82%, 15.15%, 2.25%, and 1.10% on average compared with DnCNN, RED‐CNN, CBDNet, and TSCNN, respectively. The average improvement of PSNR is 9.53%, 7.33%, 2.65%, and 3.69%, respectively. Conclusions: This paper proposed a LDCT image denoising algorithm based on end‐to‐end training. The method in this paper can effectively improve the diagnostic performance of CT images by constraining the details of the images and restoring the LDCT image structure. The problem of increased noise and artifacts in CT images can be solved while maintaining the integrity of CT image tissue structure and pathological information. Compared with other algorithms, this method has better denoising effects both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Based on high‐quality two‐dimensional seismic profiles and well data, the seismic reflection characteristics from the late Pliocene and Pleistocene succession of the Qiongdongnan Basin in the South China Sea have been analysed. The result will help in understanding the sedimentological development of slope areas. Twenty coeval clinothems are recognized and four major clinothem types are distinguished. In addition, three types of shelf‐edge trajectories are recognized. The various parameters of the clinothems are analysed quantitatively and the relationships between the various clinothem types are studied in combination with the controlling roles. It is concluded that: (i) the shelf‐edge trajectories are related to the type of clinothem; (ii) fluctuations in the relative sea level, in combination with variations in sediment supply, result in different clinothem types and geometric parameters; these parameters show interdependencies; (iii) the alternations of progradation and aggradation of clinothems may provide information of the relative sea level and changes in sediment supply; (iv) some lowstand fans could develop at the foot of the slope in the central–eastern part of the basin when the relative sea level started to fall or began to rise. The results of the present study are consequently significant for further quantitative analyses of the characteristics and development of the continental slope, not only in the Qiongdongnan Basin, but also in other basins. [ABSTRACT FROM AUTHOR]

The phase image of tapping‐mode atomic force microscopy (TM‐AFM) contains energy dissipation, which is related to the sample information on the physical properties such as the sample Young's modulus, adhesion, surface morphology and subsurface morphology. When TM‐AFM is used for sample measurement, the frequency near the first resonance peak of probe is usually selected to drive the probe vibration. When the probe vibration is driven by the frequency, the probe has a high amplitude sensitivity, but the phase sensitivity is relatively low. In this paper, the frequency at the probe phase resonance peak was selected for driving the probe vibration to measure the sample, which improved the image resolution. Phase imaging was performed on three uniform photoresist samples with different thicknesses and the same structure. When the scanning parameters were fixed and the probe setpoint value was changed alone, it was found that with the decrease of setpoint value the horizontal resolution of the phase subsurface image was decreased, and the depth sensitivity was increased first and then decreased. The result shows that TM‐AFM working at the phase resonance peak can better realise the subsurface imaging of samples at different depths. Phase subsurface imaging at the resonance can be used to quantitatively obtain subsurface phase images of different depths. [ABSTRACT FROM AUTHOR]

In order to detect the assembly quality of the combine harvester accurately and effectively, a method for the assembly quality inspection of the combine harvester based on the improved whale algorithm (IWOA) to optimize the least square support vector machine is proposed. Aiming at the characteristics of whale optimization algorithm's weak search ability and easy maturity, this paper introduces the cosine control factor and the sine time-varying adaptive weight to improve it and uses the benchmark function to verify the general adaptability of the algorithm. Combined with the local mean decomposition (LMD), the assembly quality inspection model of the combine harvester was established and applied to the Dongfanghong 4LZ-9A2 combine harvester for experimental verification. The experimental results show that the IWOA proposed in this paper has better optimization ability and adaptability. The average accuracy of the IWOA model proposed in this paper reaches 90.5%, which is 4% higher than that of the WOA model, and the standard deviation of the average accuracy is reduced by 0.15%, which indicates that the IWOA model has better stability. [ABSTRACT FROM AUTHOR]

The article presents a study which focuses on the ecosystem evapotranspiration (ET) of tropical rain forest located in Xishuangbanna, China. The study conducted an eddy covariance flux measurement at the rain forest wherein a three-dimensional sonic anometer was used to measure the wind speed and virtual temperature of eddy covariance. The study reveals that soil water availability in hot-dry season can control the ET wherein it ET is also considered to be higher during dry season.

Leaf and fig phenology (including leafing, flowering, and fruiting) and syconium growth of Ficus racemosa were studied in Xishuangbanna, China. Leaffall and flushing of F. racemosa occurred twice yearly: in mid-dry season (December to March) and mid-rainy season (July to September). The adult leaf stage of the first leaf production was remarkably longer than that of the second. F. racemosa bears syconia throughout the year, producing 4.76 crops annually. Asynchronous fig production was observed at a population level. Fig production was independent of leafing. Fig production peaks were not evident, but fluctuation was clear. Diameter growth rates of syconium were normally higher in early developmental stages than in later stages, and reached a peak coinciding with the female flower phase. The mean ± SD of syconium diameter of the female flower phase was 2.19 ± 0.36 cm, and reached 3.67 ± 0.73 cm of the male flower phase. Syconium diameter and receptacle cavity quickly enlarged at the female and male flower phases. Monthly diameter increment of the syconium was primarily affected by average monthly temperature, rather than rainfall or relative humidity. [ABSTRACT FROM AUTHOR]

Riparian vegetation is an important inhabitant of numerous forest ecosystems, although it is vulnerable and affected by the changes in climate or microclimate. Due to the fluctuation in rainfall and surface water availability, riparian plants usually exposed to two different seasons throughout the year: a dry season and a rainy season. However, water use patterns among riparian plants are still poorly understood in the tropical monsoon region. In this study, we used stable isotope techniques (δD and δ18O) coupled with MixSIAR model to identify the water sources for riparian plants in a tropical forest of SW China. The results showed an apparent seasonal variation in water use patterns for most trees, and the spatial variations were less pronounced between the terrace and floodplain sites. Among most riparian trees, deep soil (below 50 cm) was the main water source in the dry season, and shallow soil (above 15 cm) was the primary water source during the rainy season. However, there was no change in water source for herbs and other shallow‐rooted species with the fluctuation in water availability. This result indicates that shallow‐rooted plants (i.e., herbs and seedlings) struggle for their survivability in a riparian ecosystem because of the water scarcity in shallow soil during the dry season. Thus, lower rainfall and/or extended dry period may affect the productivity and sustainability of riparian vegetation under a future climate change scenario. [ABSTRACT FROM AUTHOR]