DAQE: Enhancing the Quality of Compressed Images by Finding the Secret of Defocus

• URL: http://arxiv.org/abs/2211.10984v1
• Date: Sun, 20 Nov 2022 14:08:47 GMT
• Title: DAQE: Enhancing the Quality of Compressed Images by Finding the Secret of Defocus
• Authors: Qunliang Xing, Mai Xu, Xin Deng and Yichen Guo
• Abstract summary: Existing quality enhancement approaches for compressed images neglect the inherent characteristic of defocus, resulting in inferior performance. We propose a novel dynamic region-based deep learning architecture of the DAQE approach, which considers the region-wise defocus difference of compressed images in two aspects. The DAQE approach learns to separately enhance diverse texture patterns for the regions with different defocus values, such that texture-wise one-on-one enhancement can be achieved.
• Score: 52.795238584413
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image defocus is inherent in the physics of image formation caused by the optical aberration of lenses, providing plentiful information on image quality. Unfortunately, the existing quality enhancement approaches for compressed images neglect the inherent characteristic of defocus, resulting in inferior performance. This paper finds that in compressed images, the significantly defocused regions are with better compression quality and two regions with different defocus values possess diverse texture patterns. These findings motivate our defocus-aware quality enhancement (DAQE) approach. Specifically, we propose a novel dynamic region-based deep learning architecture of the DAQE approach, which considers the region-wise defocus difference of compressed images in two aspects. (1) The DAQE approach employs fewer computational resources to enhance the quality of significantly defocused regions, while more resources on enhancing the quality of other regions; (2) The DAQE approach learns to separately enhance diverse texture patterns for the regions with different defocus values, such that texture-wise one-on-one enhancement can be achieved. Extensive experiments validate the superiority of our DAQE approach in terms of quality enhancement and resource-saving, compared with other state-of-the-art approaches.

Related papers

• DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints [26.266318338511876]
  We present DualFocus, a novel DFF framework that leverages the focal stack's unique gradient patterns induced by focus variation.<n>We show that DualFocus consistently outperforms state-of-the-art methods in both depth accuracy and perceptual quality.
  arXiv  Detail & Related papers  (2025-09-26T07:15:36Z)
• Enhancing Underwater Images Using Deep Learning with Subjective Image Quality Integration [0.8287206589886879]
  This paper presents a deep learning-based approach to improving underwater image quality.<n>We use publicly available datasets containing underwater images labeled by experts as either high or low quality.<n>Results demonstrate that the proposed model achieves substantial improvements in both perceived and measured image quality.
  arXiv  Detail & Related papers  (2025-07-07T18:25:13Z)
• Q-Ground: Image Quality Grounding with Large Multi-modality Models [61.72022069880346]
  We introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding. Q-Ground combines large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset.
  arXiv  Detail & Related papers  (2024-07-24T06:42:46Z)
• When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents [92.45867913876691]
  No-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality. We show that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement.
  arXiv  Detail & Related papers  (2024-03-11T03:35:41Z)
• Blind Image Quality Assessment Using Multi-Stream Architecture with Spatial and Channel Attention [4.983104446206061]
  BIQA (Blind Image Quality Assessment) is an important field of study that evaluates images automatically. Most algorithms generate quality without emphasizing the important region of interest. A multi-stream spatial and channel attention-based algorithm is being proposed to solve this problem.
  arXiv  Detail & Related papers  (2023-07-19T09:36:08Z)
• Optimization-Based Improvement of Face Image Quality Assessment Techniques [5.831942593046074]
  Face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. We present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. We evaluate the proposed approach in comprehensive experiments with six state-of-the-art FIQA approaches.
  arXiv  Detail & Related papers  (2023-05-24T08:06:12Z)
• Helping Visually Impaired People Take Better Quality Pictures [52.03016269364854]
  We develop tools to help visually impaired users minimize occurrences of common technical distortions. We also create a prototype feedback system that helps to guide users to mitigate quality issues.
  arXiv  Detail & Related papers  (2023-05-14T04:37:53Z)
• Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement [55.8106019031768]
  There is a growing consensus in the research community that the optimization of low-light image enhancement approaches should be guided by the visual quality perceived by end users. We propose a gap-closing framework for assessing subjective and objective quality systematically. We validate the effectiveness of our proposed framework through both the accuracy of quality prediction and the perceptual quality of image enhancement.
  arXiv  Detail & Related papers  (2023-02-22T15:57:03Z)
• Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild [9.246199263116067]
  We propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring. The proposed method consists of a learnable blur kernel to estimate the defocus map, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time.
  arXiv  Detail & Related papers  (2022-11-25T10:47:19Z)
• Learning to Deblur using Light Field Generated and Real Defocus Images [4.926805108788465]
  Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. We propose a novel deep defocus deblurring network that leverages the strength and overcomes the shortcoming of light fields.
  arXiv  Detail & Related papers  (2022-04-01T11:35:51Z)
• Image Splicing Detection, Localization and Attribution via JPEG Primary Quantization Matrix Estimation and Clustering [49.75353434786065]
  Detection of inconsistencies of double JPEG artefacts across different image regions is often used to detect local image manipulations. We propose an end-to-end system that can also distinguish regions coming from different donor images.
  arXiv  Detail & Related papers  (2021-02-02T11:21:49Z)
• Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images [54.40852143927333]
  Lossy image compression is pervasively conducted to save communication bandwidth, resulting in undesirable compression artifacts. We propose a resource-efficient blind quality enhancement (RBQE) approach for compressed images. Our approach can automatically decide to terminate or continue enhancement according to the assessed quality of enhanced images.
  arXiv  Detail & Related papers  (2020-06-30T07:38:47Z)

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.