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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE open journal of circuits and systems Jg. 5; S. 17 - 27
Hauptverfasser: Sun, Yu-Han, Lee, Chiang Lo-Hsuan, Chang, Tian-Sheuan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
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
ISSN:2644-1225, 2644-1225
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41%/15% and 53%/19% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2644-1225
2644-1225
DOI:10.1109/OJCAS.2023.3344094