The effect of display brightness and viewing distance: a dataset for visually lossless image compression

Mikhailiuk, Aliaksei; Ye, Nanyang; Mantiuk, Rafał

doi:10.2352/issn.2470-1173.2021.11.hvei-152

Cited by 11 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Luminance-aware calculation Following previous research [3,[5][6][7]26], we separately extract the luminance-aware characteristics of the reference picture I reference (Figure 2a) and the distorted image I distorted (Figure 2b). As illustrated in Figure 2, the feature detection procedure is separated into three parts: optical and retinal pathway (part I), multi-scale decomposition (part II), and neural noise simulation (part III).…”

Section: 11mentioning

confidence: 99%

“…edge_y , is the final gradient magnitude map, that is, the edge-feature map. Equation (7) shows the outcome of the edge-feature map ∆F edge between the two images:…”

Section: Spatial Feature Calculationmentioning

confidence: 99%

“…[24] K. Wolski, D. Giunchi, S. Kinuwaki, P. Didyk, K. Myszkowski, A. Steed, and R. Mantiuk, "Selecting texture resolution using a task-specific visibility metric," Computer Graphics Forum 38 (7), 685-696 (2019).…”

Section: Conflict Of Interestmentioning

confidence: 99%

See 2 more Smart Citations

Predicting visual difference maps for computer‐generated images by integrating human visual system model and deep learning

Chen

Peng

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

The quality of images generated by computer graphics rendering algorithms is mainly affected by visible distortion at some pixel locations. Image quality assessment (IQA) metrics are commonly utilized to assess the quality of rendered images, but their results are a global difference value, which does not provide pixel-wise differences to optimize the renderings. In contrast, visibility difference models including visual perception models and deep learning models can calculate pixel-wise visibility difference between distorted images and reference images. However, they either are only applied to a single type of visible distortion or are seriously dependent on datasets. To this end, the authors propose a novel model, dubbed Human Visual Perception and Deep Learning Image Difference Metric (HPDL-IDM), which combines the Human Visual System (HVS) model and deep learning. HPDL-IDM primarily consists of two modules: (i) the visual perception feature calculation module, which calculates difference maps between various kinds of features extracted from the reference image and the distorted image according to the visual characteristics of human eyes and concatenates them, and (ii) the deep learning module, which utilizes a neural network of encoder-decoder structure to train on the LocvisVC and VisTexRes datasets whose input and output are these concatenated feature difference maps and the final image distortion visibility difference map respectively. Additionally, the authors pool the final difference map into a global difference value between 0 and 1 to apply their model to many image processing tasks related to Image quality metrics (IQMs). Experimental results show that HPDL-IDM's generalization capacity and accuracy are improved by a large margin compared to other models.

show abstract

Section: 11mentioning

confidence: 99%

“…edge_y , is the final gradient magnitude map, that is, the edge-feature map. Equation (7) shows the outcome of the edge-feature map ∆F edge between the two images:…”

Section: Spatial Feature Calculationmentioning

confidence: 99%

See 1 more Smart Citation

Predicting visual difference maps for computer‐generated images by integrating human visual system model and deep learning

Chen

Peng

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Image quality has been traditionally evaluated disregarding the characteristic of the display on which the content is to be viewed. We discourage this practice, especially for HDR content, as the visibility of distortions can vary substantially with the display's peak luminance [11]. To assess image quality in a display-dependent manner, we will follow the processing shown in Hybrid-Log-Gamma (HLG) or in relative linear space, must be tone mapped for a particular HDR display.…”

Section: Background and Related Workmentioning

confidence: 99%

PU21: A novel perceptually uniform encoding for adapting existing quality metrics for HDR

Mantiuk

Azimi

2021

2021 Picture Coding Symposium (PCS)

View full text Add to dashboard Cite

Standard image quality metrics, such as PSNR or SSIM, cannot be directly computed on linear high dynamic range colour values because such values non-linearly related to our perception of visible differences. In this work, we develop a new encoding function (PU21) to convert absolute high dynamic range (HDR) linear colour values into approximately perceptually uniform (PU) values, which can be used with standard quality metrics. The proposed PU21 function is based on a recent contrast sensitivity model, fitted to the measurements up to 10 000 cd/m 2 . Unlike the conventional simplified approach of deriving PU functions based on peak sensitivities, we model realistic coding artefacts to find visibility thresholds for our derivation. Furthermore, the new PU accounts for the effect of glare on image quality. The proposed PU21 improves the accuracy of quality predictions for standard metrics of PSNR, VSI, FSIM, SSIM, and MS-SSIM in their correlation with subjective scores on HDR images included in UPIQ, one of the largest HDR image quality datasets.

show abstract

“…It is only meaningful to use photometric metrics, trained on both SDR and HDR images, for such applications as they can capture the effect of absolute luminance on image quality. A more detailed validation of such brightness-adaptive image coding can be found in [65].…”

Section: Brightness-adaptive Codingmentioning

confidence: 99%

Consolidated Dataset and Metrics for High-Dynamic-Range Image Quality

Mikhailiuk,

Perez-Ortiz,

Yue

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Increasing popularity of high-dynamic-range (HDR) image and video content brings the need for metrics that could predict the severity of image impairments as seen on displays of different brightness levels and dynamic range. Such metrics should be trained and validated on a sufficiently large subjective image quality dataset to ensure robust performance. As the existing HDR quality datasets are limited in size, we created a Unified Photometric Image Quality dataset (UPIQ) with over 4,000 images by realigning and merging existing HDR and standard-dynamic-range (SDR) datasets. The realigned quality scores share the same unified quality scale across all datasets. Such realignment was achieved by collecting additional cross-dataset quality comparisons and re-scaling data with a psychometric scaling method. Images in the proposed dataset are represented in absolute photometric and colorimetric units, corresponding to light emitted from a display. We use the new dataset to retrain existing HDR metrics and show that the dataset is sufficiently large for training deep architectures. We show the utility of the dataset on brightness aware image compression.

show abstract

The effect of display brightness and viewing distance: a dataset for visually lossless image compression

Abstract: Fast track article for IS&T International Symposium on Electronic Imaging 2021: Human Vision and Electronic Imaging 2021 proceedings.

Cited by 11 publications

References 33 publications

Predicting visual difference maps for computer‐generated images by integrating human visual system model and deep learning

Predicting visual difference maps for computer‐generated images by integrating human visual system model and deep learning

PU21: A novel perceptually uniform encoding for adapting existing quality metrics for HDR

Consolidated Dataset and Metrics for High-Dynamic-Range Image Quality

Contact Info

Product

Resources

About