IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering For Versatile Video Coding
This work addresses the challenge of improving video compression efficiency for applications like streaming by providing a more accurate and efficient JND prefiltering method, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of accurately modeling just noticeable distortion (JND) for video coding prefiltering by creating a fine-grained dataset and proposing a lightweight network, IQNet, which achieved maximum bitrate savings of up to 53% with negligible quality loss.
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.