Visual quality and algorithm efficiency are two main interests in video frame interpolation. We propose a hybrid task-based convolutional neural network for fast and accurate frame interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then reconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to preserve high-frequency information and make the synthesized frames look sharper. Experimental results show that the proposed method achieves state-of-the-art performance and performs 2.69x faster than the existing methods that are operable for 4K videos, while maintaining comparable visual and quantitative quality.Symmetry 2019, 11, 619 2 of 15 separable kernels for memory efficiency, but they still suffered from expensive computational costs. These methods not only have this problem, but also yield poor interpolation results for high-resolution video frames. The performance of these methods depends mainly on kernel size, and it is necessary to have larger kernels in order to produce good results for large motion. These methods have ghost or blur artifacts for high-resolution video frames since they tend to have larger motion. Niklaus et al. [15] proposed a context-aware synthesis approach that warps not only the input frames but also their pixel-wise contextual information, and uses them to interpolate a high-quality intermediate frame.However, this approach demands much more memory, since the pixel-wise contextual information has same resolution of input frames. Although the majority of video interpolation research [11][12][13][14][15][16][17] has focused on visual and quantitative quality, there are insufficient studies for handling high-resolution video. This is because these methods are memory intensive which is a major obstacle for interpolating high-resolution video frames.In this paper, we propose a novel hybrid task-based convolutional neural network for the fast and accurate frame interpolation of 4K videos. Our network is composed of a temporal interpolation (TI) network and a spatial interpolation (SI) network, which each have different objectives. The TI network interpolates intermediate frames, which are the same size as the downsampled input frames. The SI network reconstructs original-scale frames from the predicted intermediate frames, similar to super-resolution task [18][19][20][21]. The SI network exploits interpolation feature maps extracted from the TI network using our skip connection. To reduce the number of channels of the interpolation feature maps, we compress them into smaller dimensions, instead of concatenating as in other methods [11,14,22]. Thus, our SI network can remain shallow for good performance. This helps the network become less computational and shortens the inference time. We also propose edge loss to preserve high-frequency information and make the synthesized frames look sharper. The proposed network utilizes the YCbCr420 color format, which is commonly used for video coding as input and output, respectively. The...
Serum gastrin and pepsinogen concentrations were measured in 51 children infected with Helicobacter pylori, to investigate the clinical significance and influence of CagA and VacA on serum concentrations of these peptides. CagA+ was 44/51 (86%) and VacA+ was 42/51 (82%). Type I (CagA+/VacA+) included 39/51 (76%), type II (CagA-/VacA-) was 4/51 (8%), and intermediate (CagA-/VacA+, CagA+/VacA-) was 8/51 (16%). There was no significant correlation between endoscopic diagnosis and the state of CagA/VacA. Serum gastrin concentrations were not significantly correlated with the state of CagA/VacA. Serum pepsinogen I and II concentrations were significantly higher in CagA+ than in CagA-, but there was no significant difference between VacA+ and VacA-, Serum pepsinogen I/II ratio was not significantly correlated with the state of CagA/VacA. There was no significant difference between serum concentrations of gastrin, pepsinogen I and H. pylori phenotypes. However, pepsinogen II concentration was significantly higher in type I than type II. Pepsinogen I/II ratio was significantly lower in type I and intermediate than in type II. These findings suggest that CagA positively and phenotype of H. pylori could play a role in the development of upper gastrointestinal diseases in children.
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K frame in a single pass. In this paper, we propose a fast 4K video frame interpolation method, based upon a multi-scale optical flow reconstruction scheme. The proposed method predicts low resolution bi-directional optical flow, and reconstructs it into high resolution. We also proposed consistency and multi-scale smoothness loss to enhance the quality of the predicted optical flow. Furthermore, we use adversarial loss to make the interpolated frame more seamless and natural. We demonstrated that the proposed method outperforms the existing state-of-the-art methods in quantitative evaluation, while it runs up to 4.39× faster than those methods for 4K videos.
Steroid withdrawal followed by interferon therapy is an alternative approach for treating chronic hepatitis B virus infection when there has been no therapeutic response to interferon alone. The effectiveness of steroid withdrawal followed by interferon therapy and factors predictive of the response were evaluated in 35 children with biopsy-proven chronic hepatitis B. Patients had received a 1-month course of prednisolone, 1 mg/kg per day orally, followed by a 2-week rest, and then were treated with interferon alpha 3 MU three times per week for 4-6 months. The serum aminotransferase values normalized in 80%, and negative seroconversion rates of HBeAg and HBV-DNA were 69% and 66%. The good response rate was associated with a pretreatment HBV-DNA level lower than 100 pg/ml and a posttreatment ALT level more than 200 IU/L. Normalization of ALT values usually took 5 months, and the clearance of HBV-DNA and HBeAg took 7.8 and 6.7 months, respectively. These results suggest that steroid withdrawal followed by interferon therapy is useful in the treatment of chronic hepatitis B in children, and that a good response rate can be expected in children with lower pretreatment HBV-DNA levels (< 100 pg/ml).
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.