RESUMO
Recently, deep learning-based image quality enhancement models have been proposed to improve the perceptual quality of distorted synthesized views impaired by compression and the Depth Image-Based Rendering (DIBR) process in a multi-view video system. However, due to the lack of Multi-view Video plus Depth (MVD) data, the training data for quality enhancement models is small, which limits the performance and progress of these models. Augmenting the training data to enhance the synthesized view quality enhancement (SVQE) models is a feasible solution. In this paper, a deep learning-based SVQE model using more synthetic synthesized view images (SVIs) is suggested. To simulate the irregular geometric displacement of DIBR distortion, a random irregular polygon-based SVI synthesis method is proposed based on existing massive RGB/RGBD data, and a synthetic synthesized view database is constructed, which includes synthetic SVIs and the DIBR distortion mask. Moreover, to further guide the SVQE models to focus more precisely on DIBR distortion, a DIBR distortion mask prediction network which could predict the position and variance of DIBR distortion is embedded into the SVQE models. The experimental results on public MVD sequences demonstrate that the PSNR performance of the existing SVQE models, e.g., DnCNN, NAFNet, and TSAN, pre-trained on NYU-based synthetic SVIs could be greatly promoted by 0.51-, 0.36-, and 0.26 dB on average, respectively, while the MPPSNRr performance could also be elevated by 0.86, 0.25, and 0.24 on average, respectively. In addition, by introducing the DIBR distortion mask prediction network, the SVI quality obtained by the DnCNN and NAFNet pre-trained on NYU-based synthetic SVIs could be further enhanced by 0.02- and 0.03 dB on average in terms of the PSNR and 0.004 and 0.121 on average in terms of the MPPSNRr.
Assuntos
Compressão de Dados , Aprendizado Profundo , Aumento da Imagem/métodos , Compressão de Dados/métodosRESUMO
A method based on ultra performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) was developed for the determination of 15 water-holding functional drugs in animal tissues.The analytes were extracted with acetonitrile containing 1.0%(v/v) methanol, purified by Oasis PRiME HLB SPE column, and analyzed by Acquity UPLC BEH C18 column (50 mm×2.1 mm, 1.7 µm) using methanol and 0.1%(v/v) formic acid aqueous solution as the mobile phases.The analytes were detected using an electrospray ionization (ESI) source under the MRM mode.The calibration curves of the analytes were linear in the range of 1.0-50.0 µg/kg (r ≥ 0.9949), and the limits of quantification were all less than 1.0 µg/kg in animal tissues.The recoveries of the 15 water-holding functional drugs ranged from 60.0%-111.0% in animal tissue samples, with the intra and inter RSDs of 0.56%-11.5% and 2.31%-14.8%, respectively.The method can meet the requirements for the determination of the drug residues in animal tissues.It provides a new idea to identify potential hazards in animal-derived foods and to monitor illegal addition.