Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity

• URL: http://arxiv.org/abs/2207.08689v1
• Date: Fri, 15 Jul 2022 02:09:17 GMT
• Title: Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity
• Authors: Wei Zhou and Zhou Wang
• Abstract summary: We look at the problem of SR image quality assessment (SR IQA) in a two-dimensional (2D) space of deterministic fidelity (DF) versus statistical fidelity (SF) We propose an uncertainty weighting scheme that merges the two fidelity measures into an overall quality prediction named the Super Resolution Image Fidelity (SRIF) index.
• Score: 14.586878663223832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There has been a growing interest in developing image super-resolution (SR) algorithms that convert low-resolution (LR) to higher resolution images, but automatically evaluating the visual quality of super-resolved images remains a challenging problem. Here we look at the problem of SR image quality assessment (SR IQA) in a two-dimensional (2D) space of deterministic fidelity (DF) versus statistical fidelity (SF). This allows us to better understand the advantages and disadvantages of existing SR algorithms, which produce images at different clusters in the 2D space of (DF, SF). Specifically, we observe an interesting trend from more traditional SR algorithms that are typically inclined to optimize for DF while losing SF, to more recent generative adversarial network (GAN) based approaches that by contrast exhibit strong advantages in achieving high SF but sometimes appear weak at maintaining DF. Furthermore, we propose an uncertainty weighting scheme based on content-dependent sharpness and texture assessment that merges the two fidelity measures into an overall quality prediction named the Super Resolution Image Fidelity (SRIF) index, which demonstrates superior performance against state-of-the-art IQA models when tested on subject-rated datasets.

Related papers

• Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representations [23.04458119996]
  We propose a novel continuous low-rank factorization (CLoRF) by integrating two neural representations into the matrix factorization. This approach enables us to harness both the low rankness from the matrix factorization and the continuity from neural representation in a self-supervised manner.
  arXiv  Detail & Related papers  (2024-05-28T04:29:23Z)
• Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion [60.221404321514086]
  Multi-exposure image fusion (MEF) has emerged as a prominent solution to address the limitations of digital imaging in representing varied exposure levels. This paper presents a Hybrid-Supervised Dual-Search approach for MEF, dubbed HSDS-MEF, which introduces a bi-level optimization search scheme for automatic design of both network structures and loss functions.
  arXiv  Detail & Related papers  (2023-09-03T08:07:26Z)
• A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps [39.58198651685851]
  We propose a no-reference deep-learning image quality assessment method based on frequency maps. We first obtain the high-frequency map (HM) and low-frequency map (LM) of SRI by using Sobel operator and piecewise smooth image approximation. Our method outperforms all compared IQA models on the selected three super-resolution quality assessment (SRQA) databases.
  arXiv  Detail & Related papers  (2022-06-09T05:43:37Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment [59.91741119995321]
  We develop a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet. By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable. Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-of-the-art IQA methods, and demonstrates better consistency with the human's perspective.
  arXiv  Detail & Related papers  (2022-05-27T09:20:06Z)
• SPQE: Structure-and-Perception-Based Quality Evaluation for Image Super-Resolution [24.584839578742237]
  Super-Resolution technique has greatly improved the visual quality of images by enhancing their resolutions. It also calls for an efficient SR Image Quality Assessment (SR-IQA) to evaluate those algorithms or their generated images. In emerging deep-learning-based SR, a generated high-quality, visually pleasing image may have different structures from its corresponding low-quality image.
  arXiv  Detail & Related papers  (2022-05-07T07:52:55Z)
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging [138.04956118993934]
  We propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy.
  arXiv  Detail & Related papers  (2022-03-04T06:37:45Z)
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling [139.25215100378284]
  We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
  arXiv  Detail & Related papers  (2021-08-11T16:11:01Z)
• Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness [36.022063424485324]
  Single image super-resolution (SISR) algorithms reconstruct high-resolution (HR) images with their low-resolution (LR) counterparts. We assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness. We find that a simple linear combination of a straightforward local structural fidelity and a global statistical naturalness measures produce surprisingly accurate predictions of SISR image quality.
  arXiv  Detail & Related papers  (2021-05-15T04:31:48Z)
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
  We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
  arXiv  Detail & Related papers  (2020-12-30T03:22:46Z)
• Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks [41.558981828761574]
  We propose a no-reference/blind deep neural network-based SR image quality assessor (DeepSRQ) To learn more discriminative feature representations of various distorted SR images, the proposed DeepSRQ is a two-stream convolutional network. Experimental results on three publicly available SR image quality databases demonstrate the effectiveness and generalization ability of our proposed DeepSRQ.
  arXiv  Detail & Related papers  (2020-04-13T19:14:28Z)

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.