paper-with-me

홈 › Papers

Image Statistics Predict the Sensitivity of Perceptual Quality Metrics

2023-03-17 · Alexander Hepburn, Valero Laparra, Raúl Santos-Rodriguez, Jesús Malo

Previously, Barlow and Attneave hypothesised a link between biological vision and information maximisation. Following Shannon, information was defined using the probability of natural images. Several physiological and psychophysical phenomena have been derived from principles like info-max, efficient coding, or optimal denoising. However, it remains unclear how this link is expressed in mathematical terms from image probability. Classical derivations were subjected to strong assumptions on the probability models and on the behaviour of the sensors. Moreover, the direct evaluation of the hypothesis was limited by the inability of classical image models to deliver accurate estimates of the probability. Here, we directly evaluate image probabilities using a generative model for natural images, and analyse how probability-related factors can be combined to predict the sensitivity of state-of-the-art subjective image quality metrics, a proxy for human perception. We use information theory and regression analysis to find a simple model that when combining just two probability-related factors achieves 0.77 correlation with subjective metrics. This probability-based model is validated in two ways: through direct comparison with the opinion of real observers in a subjective quality experiment, and by reproducing basic trends of classical psychophysical facts such as the Contrast Sensitivity Function, the Weber-law, and contrast masking.

📄 PDF Abstract BibTeX arXiv:2303.09874

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingSensitivity

Similar Papers 제목 키워드 기반

Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach

2016-09-15 · Deepti Ghadiyaram, Alan C. Bovik

Current top-performing blind perceptual image quality prediction models are generally trained on legacy databases of human quality opinion scores on synthetically distorted images. Therefore they learn image features tha…

Prediction

Blind Omnidirectional Image Quality Assessment: Integrating Local Statistics and Global Semantics

2023-02-24 · Wei Zhou, Zhou Wang

Omnidirectional image quality assessment (OIQA) aims to predict the perceptual quality of omnidirectional images that cover the whole 180$\times$360$^{\circ}$ viewing range of the visual environment. Here we propose a bl…

Image Quality Assessment

On the relation between statistical learning and perceptual distances

2021-06-08 · ICLR 2022 4 · Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé 외

It has been demonstrated many times that the behavior of the human visual system is connected to the statistics of natural images. Since machine learning relies on the statistics of training data as well, the above conne…

BIG-bench Machine LearningPerceptual DistanceRelation

Assessing the ability of generative adversarial networks to learn canonical medical image statistics

2022-04-26 · Varun A. Kelkar, Dimitrios S. Gotsis, Frank J. Brooks, Prabhat KC 외

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well …

Image GenerationImage Quality AssessmentTranslation

Learn to Evaluate Image Perceptual Quality Blindly from Statistics of Self-similarity

2015-10-10 · Wufeng Xue, Xuanqin Mou, Lei Zhang

Among the various image quality assessment (IQA) tasks, blind IQA (BIQA) is particularly challenging due to the absence of knowledge about the reference image and distortion type. Features based on natural scene statisti…

Image Quality Assessment