Performance Analysis of JPEG XR with Deep Learning-Based Image Super-Resolution

The demand for efficient and high-level image and video codec compression has been widely increasing. Conventional image compression methods such as JPEG XR use a high quantization parameter (QP) to produce a highly compressed file for any given image. However, higher QP has unpleasing artifacts that lead to perceptual quality degradation. A feasible solution to tackle this limitation is to reduce the high-resolution image size by downsampling it before encoding with JPEG XR. Then, the super-resolution algorithm is applied to the resultant low-resolution image to reconstruct the high-resolution result. In this paper, we downsample the input image before JPEG XR. Then, we investigate the performance of integrating deep learning-based FSRCNN super-resolution (SR) with JPEG XR in terms of quality and compressed file size. According to the experimental results, the fusion of image super-resolution and conventional image coding standard outperforms the JPEG XR enmnressinn.