Perceptual Quality Study On Deep Learning Based Image Compression
Recently 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.
WOS:000521828600143
2019-01-01
978-1-5386-6249-6
New York
IEEE International Conference on Image Processing ICIP
719
723
REVIEWED
Event name | Event place | Event date |
Taipei, TAIWAN | Sep 22-25, 2019 | |