Image Super-Resolution Quality Assessment: Structural Fidelity Versus
Statistical Naturalness
- URL: http://arxiv.org/abs/2105.07139v1
- Date: Sat, 15 May 2021 04:31:48 GMT
- Title: Image Super-Resolution Quality Assessment: Structural Fidelity Versus
Statistical Naturalness
- Authors: Wei Zhou, Zhou Wang, Zhibo Chen
- Abstract summary: 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.
- Score: 36.022063424485324
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Single image super-resolution (SISR) algorithms reconstruct high-resolution
(HR) images with their low-resolution (LR) counterparts. It is desirable to
develop image quality assessment (IQA) methods that can not only evaluate and
compare SISR algorithms, but also guide their future development. In this
paper, we assess the quality of SISR generated images in a two-dimensional (2D)
space of structural fidelity versus statistical naturalness. This allows us to
observe the behaviors of different SISR algorithms as a tradeoff in the 2D
space. Specifically, SISR methods are traditionally designed to achieve high
structural fidelity but often sacrifice statistical naturalness, while recent
generative adversarial network (GAN) based algorithms tend to create more
natural-looking results but lose significantly on structural fidelity.
Furthermore, such a 2D evaluation can be easily fused to a scalar quality
prediction. Interestingly, 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 when
tested using public subject-rated SISR image datasets. Code of the proposed
SFSN model is publicly available at \url{https://github.com/weizhou-geek/SFSN}.
Related papers
- Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment [25.88845910499606]
We propose a novel dual-branch reduced-reference SR-IQA network, ie, Perception- and Fidelity-aware SR-IQA (PFIQA)
PFIQA outperforms current state-of-the-art models across three widely-used SR-IQA benchmarks.
arXiv Detail & Related papers (2024-05-15T16:09:22Z) - Exploiting Self-Supervised Constraints in Image Super-Resolution [72.35265021054471]
This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR.
SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability.
Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR.
arXiv Detail & Related papers (2024-03-30T06:18:50Z) - DeepDC: Deep Distance Correlation as a Perceptual Image Quality
Evaluator [53.57431705309919]
ImageNet pre-trained deep neural networks (DNNs) show notable transferability for building effective image quality assessment (IQA) models.
We develop a novel full-reference IQA (FR-IQA) model based exclusively on pre-trained DNN features.
We conduct comprehensive experiments to demonstrate the superiority of the proposed quality model on five standard IQA datasets.
arXiv Detail & Related papers (2022-11-09T14:57:27Z) - Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessment [60.88265569998563]
We make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined.
We empirically show that the statistics deviation could be effectively leveraged in quality assessment.
arXiv Detail & Related papers (2022-09-12T15:26:13Z) - Quality Assessment of Image Super-Resolution: Balancing Deterministic
and Statistical Fidelity [14.586878663223832]
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.
arXiv Detail & Related papers (2022-07-15T02:09:17Z) - 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) - 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) - Structure-Preserving Image Super-Resolution [94.16949589128296]
Structures matter in single image super-resolution (SISR)
Recent studies have promoted the development of SISR by recovering photo-realistic images.
However, there are still undesired structural distortions in the recovered images.
arXiv Detail & Related papers (2021-09-26T08:48:27Z) - 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.