Towards Modelling of Visual Saliency in Point Clouds for Immersive Applications

Alexiou, Evangelos; Xu, Peisen; Ebrahimi, Touradj

doi:10.1109/icip.2019.8803479

Cited by 15 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas for the contents assessed in test T2 a large difference was observed between codec V-PCC and the MPEG anchor, for the contents in test T1 the gap was markedly lower, and indeed the significance of the effect of the codec selection had a smaller effect size for test T1 with respect to test T2, as seen in section 4.1. Test T2 consisted of contents that had been used in multiple quality assessment experiments [8,9,11,36], notably including the performance evaluation of the upcoming MPEG standard [32]. On the other hand, test T1 included contents that have not been used so far in assessment of point cloud compression solutions.…”

Section: Datasetsmentioning

confidence: 99%

Comparing the Quality of Highly Realistic Digital Humans in 3DoF and 6DoF: A Volumetric Video Case Study

Subramanyam¹,

Li²,

Viola³

et al. 2020

2020 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

View full text Add to dashboard Cite

show abstract

Section: Datasetsmentioning

confidence: 99%

Comparing the Quality of Highly Realistic Digital Humans in 3DoF and 6DoF: A Volumetric Video Case Study

Subramanyam¹,

Li²,

Viola³

et al. 2020

2020 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

View full text Add to dashboard Cite

show abstract

“…Whereas for the contents assessed in test T2 a large difference was observed between codec V-PCC and the MPEG anchor, for the contents in test T1 the gap was markedly lower, and indeed the significance of the effect of the codec selection had a smaller effect size for test T1 with respect to test T2, as seen in section 4.1. Test T2 consisted of contents that had been used in multiple quality assessment experiments [7,8,37,44,47], notably including the performance evaluation of the upcoming MPEG standard [43]. On the other hand, test T1 included contents that have not been used so far in assessment of point cloud compression solutions.…”

Section: Datasetsmentioning

confidence: 99%

“…Previous research on subjective assessment of dynamic point cloud contents has been primarily conducted in desktop setups [2,52], whereas VR/AR technologies have been employed with static content [6,8], or limited amount of dynamic contents [53]. However, placing dynamic contents to be rendered in a VR/AR environment in real time, in order for users to interact, adds several technological constraints.…”

Section: Rendering Environment Considerationsmentioning

confidence: 99%

On the impact of VR assessment on the Quality of Experience of Highly Realistic Digital Humans

Viola¹,

Subramanyam²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fuelled by the increase in popularity of virtual and augmented reality applications, point clouds have emerged as a popular 3D format for acquisition and rendering of digital humans, thanks to their versatility and real-time capabilities. Due to technological constraints and real-time rendering limitations, however, the visual quality of dynamic point cloud contents is seldom evaluated using virtual and augmented reality devices, instead relying on prerecorded videos displayed on conventional 2D screens. In this study, we evaluate how the visual quality of point clouds representing digital humans is affected by compression distortions. In particular, we compare three different viewing conditions based on the degrees of freedom that are granted to the viewer: passive viewing (2DTV), head rotation (3DoF), and rotation and translation (6DoF), to understand how interacting in the virtual space affects the perception of quality. We provide both quantitative and qualitative results of our evaluation involving 78 participants, and we make the data publicly available. To the best of our knowledge, this is the first study evaluating the quality of dynamic point clouds in virtual reality, and comparing it to traditional viewing settings. Results highlight the dependency of visual quality on the content under test, and limitations in the way current data sets are used to evaluate compression solutions. Moreover, influencing factors in quality evaluation in VR, and shortcomings in how point cloud This work is funded by the European Commission H2020 program, under the grant agreement 762111, VRTogether, http://vrtogether.eu/.

show abstract

“…All of these are adopted into the MPEG point cloud compression reference software [34] for compression efficiency measurement. Later as analyzed extensively by EPFL lab members in their serial publications [16], [33], [39]- [41], [43], [45], [48], these point-wise distance based metrics are not well correlated with the subjective assessments with unreliable prediction accuracy. [49], [50] also tested the performance of these metrics under the distortion caused by typical compression methods, such as MPEG Point cloud Test Model Category 2 (TMC2) [51] and reached the same conclusion.…”

Section: Related Workmentioning

confidence: 99%

Inferring Point Cloud Quality via Graph Similarity

Yang¹,

Ma²,

Yan³

et al. 2020

Preprint

View full text Add to dashboard Cite

Objective quality estimation of media content plays a vital role in vast applications. Though numerous metrics have been successfully devised for 2D image or video, it still lacks of a counterpart for emerging 3D point clouds with unstructured and sparsely distributed points. We propose the GraphSIM -an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments. Motivated by the facts that human vision system is more sensitive to the high spatial-frequency components (e.g., contours, edges), and weighs more to the local structural variations rather individual point intensity, we first extract geometric keypoints by resampling the reference point cloud geometry information to form the object skeleton; we then construct local graphs centered at these keypoints for both reference and distorted point clouds, followed by collectively aggregating color gradient moments (e.g., zeroth, first, and second) that are derived between all other points and centered keypoint in the same local graph for significant feature similarity (a.k.a., local significance) measurement; Final similarity index is obtained by pooling the local graph significance across all color channels and by averaging across all graphs. Our GraphSIM is validated using two large and independent point cloud assessment datasets that involve a wide range of impairments (e.g., re-sampling, compression, additive noise), reliably demonstrating the state-of-the-art performance for all distortions with noticeable gains in predicting the subjective mean opinion score (MOS), compared with those point-wise distance-based metrics adopted in standardization reference software. Ablation studies have further shown that GraphSIM is generalized to various scenarios with consistent performance by examining its key modules and parameters. Models and associated materials will be made to public at https://njuvision.github.io/GraphSIM or http://smt.sjtu.edu.cn/papers/GraphSIM.

show abstract

Towards Modelling of Visual Saliency in Point Clouds for Immersive Applications

Cited by 15 publications

References 22 publications

Comparing the Quality of Highly Realistic Digital Humans in 3DoF and 6DoF: A Volumetric Video Case Study

Comparing the Quality of Highly Realistic Digital Humans in 3DoF and 6DoF: A Volumetric Video Case Study

On the impact of VR assessment on the Quality of Experience of Highly Realistic Digital Humans

Inferring Point Cloud Quality via Graph Similarity

Contact Info

Product

Resources

About