Cheng, ZhengxueAkyazi, PinarSun, HemingKatto, JiroEbrahimi, Touradj2020-04-172020-04-172020-04-172019-01-0110.1109/ICIP.2019.8803824https://infoscience.epfl.ch/handle/20.500.14299/168224WOS:000521828600143Recently deep learning based image compression has made rapid advances with promising results based on objective quality metrics. However, a rigorous subjective quality evaluation on such compression schemes have rarely been reported. This paper aims at perceptual quality studies on learned compression. First, we build a general learned compression approach, and optimize the model. In total six compression algorithms are considered for this study. Then, we perform subjective quality tests in a controlled environment using high-resolution images. Results demonstrate learned compression optimized by MS-SSIM yields competitive results that approach the efficiency of state-of-the-art compression. The results obtained can provide a useful benchmark for future developments in learned image compression.subjective and objective quality evaluationlearning image compressioncompression standardstext::conference output::conference proceedings::conference paper