The video super-resolution (VSR) task aims to restore a high-resolution video frame by using its corresponding low-resolution frame and multiple neighboring frames. At present, many deep learning-based VSR methods rely on optical flow to perform frame alignment. The final recovery results will be greatly affected by the accuracy of optical flow. However, optical flow estimation cannot be completely accurate, and there are always some errors. In this paper, we propose a novel deformable non-local network (DNLN) which is non-flow-based. Specifically, we apply the improved deformable convolution in our alignment module to achieve adaptive frame alignment at the feature level. Furthermore, we utilize a non-local module to capture the global correlation between the reference frame and aligned neighboring frame, and simultaneously enhance desired fine details in the aligned frame. To reconstruct the final high-quality HR video frames, we use residual in residual dense blocks to take full advantage of the hierarchical features. Experimental results on several datasets demonstrate that the proposed DNLN can achieve state of the art performance on video super-resolution task.
The effect of source and sink manipulation on accumulation of micronutrients (Fe, Zn, Mn, Cu) and protein in wheat grains was studied in a field experiment and ear culture. The source and sink manipulation was obtained by reducing assimilate source (through defoliation and spike shading) or sink (through 50% spikelets removal) after anthesis in the field and by changing sucrose or NH 4 NO 3 levels of the culture media in ear culture. In the field experiment, reducing source and sink generally increased Fe, Zn, Mn, Cu, and protein concentrations except defoliation which decreased Mn concentration. Grain yield as well as micronutrient and protein contents in grains were all reduced by reducing source and sink sizes, suggesting that the accumulation of micronutrients and protein in grains was restricted by source supply and sink capacity. In ear culture, the supply of 20 to 80 g L -1 sucrose increased grain weight and yield, but decreased grain Fe, Zn, Mn, Cu, and protein concentrations. The supply of 0.57 to 2.28 g L -1 NH 4 NO 3 increased grain yield and the concentrations and contents of micronutrients and protein. All these results show that micronutrient and protein accumulation in grains can be affected by the source-sink relationship of carbohydrate and nitrogen. Adequate N supply can simultaneously increase grain yield and the accumulation of Fe, Zn, Mn, Cu, and protein.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.