21 July 2023 in Frontiers in Plant Science
Abiotic stresses pose significant threat to horticultural crop production worldwide. These stresses adversely affect plant growth, development, and ultimately declined crop growth, yield and quality. In recent years, plant scientists have been actively investigating innovative strategies to enhance abiotic stress resilience in crops, and one promising avenue of research focuses on the use of brassinosteroids (BRs). BRs are a class of plant hormones that play crucial roles in various physiological processes, including cell elongation, differentiation, and stress responses. They have emerged as potent regulators of plant growth and development, and their role in improving abiotic stress tolerance is gaining considerable attention. BRs have been shown to mitigate the negative effects of abiotic stresses by modulating key physiological and biochemical processes, including stomatal regulation, antioxidant defense, osmotic adjustment, and nutrient uptake. Abiotic stresses disrupt numerous physiological functions and lead to undesirable phenotypic traits in plants. The use of BRs as a tool to improve crop resilience offers significant promise for sustainable agriculture in the face of increasing abiotic stresses caused by climate change. By unraveling the phenomenon of BRs, this review emphasizes the potential of BRs as an innovative approach for boosting abiotic stress tolerance and improving the overall productivity and quality of horticultural crops. Further research and field trials are necessary to fully harness the benefits of BRs and translate these findings into practical applications for crop production systems.
20 March 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefSR in a self-supervised manner. Particularly, we propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms. Firstly, considering the popularity of multiple cameras in modern smartphones, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide the super-resolution (SR) of the lesser zoomed (ultra-wide) image, which gives us a chance to learn a deep network that performs SR from the dual zoomed observations (DZSR). Secondly, for self-supervised learning of DZSR, we take the telephoto image instead of an additional high-resolution image as the supervision information, and select a center patch from it as the reference to super-resolve the corresponding ultra-wide image patch. To mitigate the effect of the misalignment between ultra-wide low-resolution (LR) patch and telephoto ground-truth (GT) image during training, we first adopt patch-based optical flow alignment to obtain the warped LR, then further design an auxiliary-LR to guide the deforming of the warped LR features. To generate visually pleasing results, we present local overlapped sliced Wasserstein loss to better represent the perceptual difference between GT and output in the feature space. During testing, DZSR can be directly deployed to super-solve the whole ultra-wide image with the reference of the telephoto image. In addition, we further take multiple zoomed observations to explore self-supervised RefSR, and present a progressive fusion scheme for the effective utilization of reference images. Experiments show that our methods achieve better quantitative and qualitative performance against state-of-the-arts. The code and pre-trained models will be publicly available.
23 December 2024 in IEEE Transactions on Multimedia
Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments. Leveraging near-infrared (NIR) images to assist visible RGB image denoising shows the potential to address this issue, becoming a promising technology. Nonetheless, existing works still struggle with taking advantage of NIR information effectively for real-world image denoising, due to the content inconsistency between NIR-RGB images and the scarcity of real-world paired datasets. To alleviate the problem, we propose an efficient Selective Fusion Module (SFM), which can be plug-and-played into the advanced denoising networks to merge the deep NIR-RGB features. Specifically, we sequentially perform the global and local modulation for NIR and RGB features, and then integrate the two modulated features. Furthermore, we present a Real-world NIR-Assisted Image Denoising (Real-NAID) dataset, which covers diverse scenarios as well as various noise levels. Extensive experiments on both synthetic and our real-world datasets demonstrate that the proposed method achieves better results than state-of-the-art ones. The dataset, codes, and pre-trained models will be publicly available.