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

• URL: http://arxiv.org/abs/2312.09799v1
• Date: Fri, 15 Dec 2023 13:58:10 GMT
• Title: IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering For Versatile Video Coding
• Authors: Yu-Han Sun, Chiang Lo-Hsuan Lee and Tian-Sheuan Chang
• Abstract summary: Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual way by filtering the perceptually redundant information prior to compression. This paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling.
• Score: 0.9403328689534943
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• SG-JND: Semantic-Guided Just Noticeable Distortion Predictor For Image Compression [50.2496399381438]
  Just noticeable distortion (JND) represents the threshold of distortion in an image that is minimally perceptible to the human visual system. Traditional JND prediction methods only rely on pixel-level or sub-band level features. We propose a Semantic-Guided JND network to leverage semantic information for JND prediction.
  arXiv  Detail & Related papers  (2024-08-08T07:14:57Z)
• Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler [103.97487121678276]
  Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs. We propose a novel Knowledge-driven Differential Filter Sampler(KDFS) with Masked Filter Modeling(MFM) framework for filter pruning.
  arXiv  Detail & Related papers  (2023-07-01T02:28:41Z)
• High-Perceptual Quality JPEG Decoding via Posterior Sampling [13.238373528922194]
  We propose a different paradigm for JPEG artifact correction. We aim to obtain sharp, detailed and visually reconstructed images, while being consistent with the compressed input. Our solution offers a diverse set of plausible and fast reconstructions for a given input with perfect consistency.
  arXiv  Detail & Related papers  (2022-11-21T19:47:59Z)
• Just Noticeable Difference Modeling for Face Recognition System [69.28990314553076]
  We make the first attempt to study just noticeable difference (JND) for the automatic face recognition system. We develop a novel JND prediction model to directly infer JND images for the FR system. Experimental results have demonstrated that the proposed model achieves higher accuracy of JND map prediction.
  arXiv  Detail & Related papers  (2022-09-13T10:06:36Z)
• DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization [14.062386668676533]
  We propose a novel Deep Comprehensible Color Filter (DCCF) learning framework for high-resolution image harmonization. DCCF learns four human comprehensible neural filters (i.e. hue, saturation, value and attentive rendering filters) in an end-to-end manner. It outperforms state-of-the-art post-processing method on iHarmony4 dataset on images' full-resolutions by achieving 7.63% and 1.69% relative improvements on MSE and PSNR respectively.
  arXiv  Detail & Related papers  (2022-07-11T11:42:10Z)
• Towards Top-Down Just Noticeable Difference Estimation of Natural Images [65.14746063298415]
  Just noticeable difference (JND) estimation mainly dedicates to modeling the visibility masking effects of different factors in spatial and frequency domains. In this work, we turn to a dramatically different way to address these problems with a top-down design philosophy. Our proposed JND model can achieve better performance than several latest JND models.
  arXiv  Detail & Related papers  (2021-08-11T06:51:50Z)
• Perceptually-inspired super-resolution of compressed videos [18.72040343193715]
  spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. Recent work has employed advanced super-resolution methods based on convolutional neural networks (CNNs) to further improve reconstruction quality. In this paper, a perceptually-inspired super-resolution approach (M-SRGAN) is proposed for spatial upsampling of compressed video using a modified CNN model.
  arXiv  Detail & Related papers  (2021-06-15T13:50:24Z)
• UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models [8.484676769284578]
  We propose a generic scale-aware self-supervised pipeline for estimating depth, euclidean distance, and visual odometry from unrectified monocular videos. The proposed algorithm is evaluated further on the KITTI rectified dataset, and we achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2020-07-13T20:35:05Z)
• Perceptually Optimizing Deep Image Compression [53.705543593594285]
  Mean squared error (MSE) and $ell_p$ norms have largely dominated the measurement of loss in neural networks. We propose a different proxy approach to optimize image analysis networks against quantitative perceptual models.
  arXiv  Detail & Related papers  (2020-07-03T14:33:28Z)
• Quantization Guided JPEG Artifact Correction [69.04777875711646]
  We develop a novel architecture for artifact correction using the JPEG files quantization matrix. This allows our single model to achieve state-of-the-art performance over models trained for specific quality settings.
  arXiv  Detail & Related papers  (2020-04-17T00:10:08Z)
• CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance [2.876893463410366]
  We propose a novel direction to improve the denoising quality of filtering-based denoising algorithms in real time. We take the use case of BM3D, the state-of-the-art filtering-based denoising algorithm, to demonstrate and validate our approach.
  arXiv  Detail & Related papers  (2020-01-20T03:46:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.