HEVC Image Quality Assessment of the Multi-view and Super-resolution Images Based on CNN

To read the file of this research, you can request a copy directly from the author.


We can come to approach on super-resolution processing based on deep learning by appearing deep learning tools. These performance are shown by applying the only deep learning theory for super-resolution processing. However, we consider that the optimal condition and design for super-resolution processing are achieved better by improving these algorithms and setting parameter appropriately. In this paper, first, we carried out experiments on optimal condition and design of super-resolution processing for the multi-view 3D images encoded and decoded by H.265/HEVC, focused on structure of convolutional neural network by using Chainer. And then, we assessed for the generated images quality objectively, and compare to each image. Finally, we discussed for experimental results.

No file available

Request Full-text Paper PDF

To read the file of this research,
you can request a copy directly from the author.

... In the broadcasting research field, the TV broadcasting of 4K (Quad FHDTV (QFHDTV)) image quality four times more than that of 2K (Full HDTV (FHDTV)) thus far, which was started in BS 4K broadcasting since December 2018. Therefore, we are starting to feel changing of high-definition and high-resolution image and video everyday life [1]. On the other hand, by appearing of the super speed optical Internet communication, it comes increase rapidly for image information to send and receive. ...
In this paper, first, we carried out dictionary learning to process the sparse coding in advance, and then, we added six types of noise for 3D CG images. Next, we processed noise removal based on sparse coding theory and dictionary learning. Before and after image processing, we discussed improvement of image quality evaluation value eventually by measuring PSNR.
... On the other hand, since even if 4K broadcasting is started, all broadcasting video contents are not in 4K video quality, it is difficult to represent texture or shitsukan of images originally. Therefore, for an example, HDTV quality video is transformed to 4K quality by processing of super-resolution [1], and then, we will need to reproduce texture of 4K quality as possible in the near future. Up to now, in "Shitsukan (in Japanese)", there are a lot of meaning and interpretation. ...
ResearchGate has not been able to resolve any references for this publication.