Perceptual Representations of Structural Information in Images: Application to Quality Assessment of Synthesized View in FTV Scenario

Ling, Suiyi; Li, Jing; Callet, Patrick Le; Wang, Junle

doi:10.1109/icip.2019.8803105

Cited by 5 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the free viewpoint videos (FVV) and multi-view videos (MVV) provide the images from multiple viewpoints at the same time instant. The temporal distortions in FVV or MVV are mainly introduced by the changing of viewpoints instead of timeline [48], [74]. This type of distortions are different from that in normal DIBRsynthesized views videos.…”

Section: Discussionmentioning

confidence: 96%

See 1 more Smart Citation

Quality assessment of DIBR-synthesized views: An overview

et al. 2021

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 96%

“…objects, unnatural structures. Besides, there are also some hierarchical metrics which combine the above features, such as the LMS metric proposed in [47] which uses both low-level and mid-level features [39] and the metric in [48] which integrates the features on each level.…”

Section: Discussionmentioning

confidence: 99%

Quality assessment of DIBR-synthesized views: An overview

et al. 2021

View full text Add to dashboard Cite

“…The first group of metrics used for comparison designed to evaluate quality of DIBR-synthesized images, which use machine learning-based techniques, contains no-reference models, LVGC [20], SET [31], CSC-NRM [42] and referencebased models, Q [33], Q [32], ST-IQM [34] and LMS [23]. The proposed DoC-DoG-GRNN model is a no-reference machine learning-based technique.…”

Section: E Comparison Of the Proposed Model To Other Iqa Modelsmentioning

confidence: 99%

“…The performances of the reference-based models designed to evaluate the quality of DIBR-synthesized images using machine learning techniques, Q [33], Q [32], ST-SIQM [34] and LMS [23] are taken from the papers where they were introduced. Q [33] quantifies the impact of structure-related distortion on perceived quality of synthesized images using the low-level contour descriptor, the mid-level contour category descriptor and the task-oriented non-natural structure descriptor.…”

Section: E Comparison Of the Proposed Model To Other Iqa Modelsmentioning

confidence: 99%

Quality Assessment of DIBR-Synthesized Views Based on Sparsity of Difference of Closings and Difference of Gaussians

Sandic-Stankovic¹,

Kukolj

Callet

2022

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Images synthesized using depth-imagebasedrendering (DIBR) techniques may suffer from complex structural distortions. The goal of the primary visual cortex and other parts of brain is to reduce redundancies of input visual signal in order to discover the intrinsic image structure, and thus create sparse image representation. Human visual system (HVS) treats images on several scales and several levels of resolution when perceiving the visual scene. With an attempt to emulate the properties of HVS, we have designed the no-reference model for the quality assessment of DIBR-synthesized views. To extract a higher-order structure of high curvature which corresponds to distortion of shapes to which the HVS is highly sensitive, we define a morphological oriented Difference of Closings (DoC) operator and use it at multiple scales and resolutions. DoC operator nonlinearly removes redundancies and extracts fine grained details, texture of an image local structure and contrast to which HVS is highly sensitive. We introduce a new feature based on sparsity of DoC band. To extract perceptually important loworder structural information (edges), we use the non-oriented Difference of Gaussians (DoG) operator at different scales and resolutions. Measure of sparsity is calculated for DoG bands to get scalar features. To model the relationship between the extracted features and subjective scores, the general regression neural network (GRNN) is used. Quality predictions by the proposed DoC-DoG-GRNN model show higher compatibility with perceptual quality scores in comparison to the tested state-of-theart metrics when evaluated on four benchmark datasets with synthesized views, IRCCyN/IVC image/video dataset, MCL-3D stereoscopic image dataset and IST image dataset.

show abstract

“…It is proven in [12] that the image quality assessment procedure within the human visual system also adheres to the strategy of 'sparse coding' [13]. Based on this fact, CSC was exploited to quantify structure-related artifacts in several immersive applications [14,15,16]. We collected a set of distorted patches from EPI slices and trained a CSC codebook, where each element within the codebook represent a certain type of non-natural structure that could be observed in EPI slices.…”

Section: Convolutional Sparse Codingmentioning

confidence: 99%

No-Reference Quality Evaluation of Light Field Content Based on Structural Representation of The Epipolar Plane Image

Ak¹,

Ling²,

Callet³

2020

2020 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

Self Cite

View full text Add to dashboard Cite

As an emerging technology, Light Field (LF) has gained everincreasing importance in the domain. In order to provide guidance for the development of perceptually accurate Light Field (LF) processing tools and supervise the entire streaming system, robust perceptual quality assessment metrics are required. Especially, No-Reference (NR) metrics are preferable to compare LF with different angular resolutions. Some metrics have been developed by extending commonly used 2D image quality metrics to the 4D LF domain with angular consistency terms. Nonetheless, although these models consistently show slightly improved performance, most of them are limited in evaluating the quality of LF using the sub-aperture views with additional terms on the angular domain. There is an evident lack of reliable quality metrics that are tailored to LF content. To remedy this lack, we propose a NR quality metric for LF contents based on representing EPI with structural descriptors, including the Histogram of Gradients and the Convolutional Sparse Coding based descriptors. The primary motivation resides in our observations that (1) LF related distortions on the angular domain are highly noticeable on the Epipolar Plane Image representations (EPI); (2) most of the distortions in EPI are structurerelated. Extensive experiments on the MPI-LFA [1] LF image quality dataset demonstrate that our method provides competitive performance with the state-of-the-art NR image quality metrics.

show abstract

Perceptual Representations of Structural Information in Images: Application to Quality Assessment of Synthesized View in FTV Scenario

Cited by 5 publications

References 32 publications

Quality assessment of DIBR-synthesized views: An overview

Quality assessment of DIBR-synthesized views: An overview

Quality Assessment of DIBR-Synthesized Views Based on Sparsity of Difference of Closings and Difference of Gaussians

No-Reference Quality Evaluation of Light Field Content Based on Structural Representation of The Epipolar Plane Image

Contact Info

Product

Resources

About