IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

• Published in: IEEE open journal of circuits and systems Vol. 5; pp. 17 - 27
• Main Authors: Sun, Yu-Han, Lee, Chiang Lo-Hsuan, Chang, Tian-Sheuan
• Format: Journal Article
• Language: English
• Published: New York IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Codecs; Datasets; Deep learning; Discrete cosine transforms; Distortion; Encoding; Image coding; Image edge detection; Image enhancement; Image quality; Image reconstruction; just noticeable distortion; Quality assessment; Training data; Video coding; video quality assessment

Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level s...