A Review of Existing Evaluation Methods for Point Clouds Quality

Fretes, Héctor; Gomez-Redondo, Marcos; Paiva, Enrique; Rodas, Jorge; Gregor, Raúl

doi:10.1109/reduas47371.2019.8999725

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each point in the sparse cloud has four accuracy attributes: the reconstruction accuracy (RA), the reprojection error (RE), the projection accuracy (PA) and the image count [35]. In particular, the RE is suggested as the quality measure of tie points [20,36]. It is the deviation of the positions of identified features in the original image from positions of the same features in the calculated 3D space.…”

Section: Optimizing the Georeferencingmentioning

confidence: 99%

Quality Assessment of Photogrammetric Methods—A Workflow for Reproducible UAS Orthomosaics

et al. 2020

View full text Add to dashboard Cite

Unmanned aerial systems (UAS) are cost-effective, flexible and offer a wide range of applications. If equipped with optical sensors, orthophotos with very high spatial resolution can be retrieved using photogrammetric processing. The use of these images in multi-temporal analysis and the combination with spatial data imposes high demands on their spatial accuracy. This georeferencing accuracy of UAS orthomosaics is generally expressed as the checkpoint error. However, the checkpoint error alone gives no information about the reproducibility of the photogrammetrical compilation of orthomosaics. This study optimizes the geolocation of UAS orthomosaics time series and evaluates their reproducibility. A correlation analysis of repeatedly computed orthomosaics with identical parameters revealed a reproducibility of 99% in a grassland and 75% in a forest area. Between time steps, the corresponding positional errors of digitized objects lie between 0.07 m in the grassland and 0.3 m in the forest canopy. The novel methods were integrated into a processing workflow to enhance the traceability and increase the quality of UAS remote sensing.

show abstract

Section: Optimizing the Georeferencingmentioning

confidence: 99%

Quality Assessment of Photogrammetric Methods—A Workflow for Reproducible UAS Orthomosaics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ essential to develop effective methods that accurately assess the quality of PC and preserve the quality of the user experience. Two families of methods are usually adopted to evaluate PC degradation [11], [12], [13]: subjective and objective metrics. The subjective ones are based on human judgment for the evaluation, which makes it cumbersome and expansive in practical real-world situations.…”

Section: Introductionmentioning

confidence: 99%

No-Reference 3D Point Cloud Quality Assessment Using Multi-View Projection and Deep Convolutional Neural Network

et al. 2023

View full text Add to dashboard Cite

Digital representation of 3D content in the form of 3D point clouds (PC) has gained increasing interest and has emerged in various computer vision applications. However, various degradation may appear on the PC during acquisition, transmission, or treatment steps in the 3D processing pipeline. Therefore, several Full-Reference, Reduced-Reference, and No-Reference metrics have been proposed to estimate the visual quality of PC. However, Full-Reference and Reduced-Reference metrics require reference information, which is not accessible in real-world applications, and No-Reference metrics still lack precision in evaluating the PC quality. In this context, we propose a novel deep learning-based method for No-Reference Point Cloud Quality Assessment (NR-PCQA) that aims to automatically predict the perceived visual quality of the PC without using the reference content. More specifically, in order to imitate the human visual system during the PC quality evaluation that captures the geometric and color degradation, we render the PC into different 2D views using a perspective projection. Then, the projected 2D views are divided into patches that are fed to a Convolutional Neural Network (CNN) to learn sophisticated and discriminative visual quality features for evaluating the local quality of each patch. Finally, the overall quality score of the PC is obtained by pooling the quality score patches. We conduct extensive experiments on three benchmark databases: ICIP2020, SJTU, and WPC, and we compare the proposed model to the existing Full-Reference, Reduced-Reference, and No-Reference state-of-the-art methods. Based on the experimental results, our proposed model achieves high correlations with the subjective quality scores and outperforms the state-of-the-art methods.INDEX TERMS Point cloud, quality assessment, point cloud rendering, convolutional neural network (CNN).

show abstract

New challenges in point cloud visual quality assessment: a systematic review

Tious,

Vigier,

Ricordel

2024

Front. Signal Process.

View full text Add to dashboard Cite

The compression, transmission and rendering of point clouds is essential for many use cases, notably immersive experience settings in eXtended Reality, telepresence and real-time communication where real world acquired 3D content is displayed in a virtual or real scene. Processing and display for these applications induce visual artifacts and the viewing conditions can impact the visual perception and Quality of Experience of users. Therefore, point cloud codecs, rendering methods, display settings and more need to be evaluated through visual Point Cloud Quality Assessment (PCQA) studies, both subjective and objective. However, the standardization of recommendations and methods to run such studies did not follow the evolution of the research field and new issues and challenges have emerged. In this paper, we make a systematic review of subjective and objective PCQA studies. We collected scientific papers from online libraries (IEEE Xplore, ACM DL, Scopus) and selected a set of relevant papers to analyze. From our observations, we discuss the progress and future challenges in PCQA toward efficient point cloud video coding and rendering for eXtended Reality. Main axes for development include the study of use case specific influential factors and the definition of new test conditions for subjective PCQA, and development of perceptual learning-based methods for objective PCQA metrics as well as more versatile evaluation of their performance and time complexity.

show abstract

A Review of Existing Evaluation Methods for Point Clouds Quality

Cited by 4 publications

References 34 publications

Quality Assessment of Photogrammetric Methods—A Workflow for Reproducible UAS Orthomosaics

Quality Assessment of Photogrammetric Methods—A Workflow for Reproducible UAS Orthomosaics

No-Reference 3D Point Cloud Quality Assessment Using Multi-View Projection and Deep Convolutional Neural Network

New challenges in point cloud visual quality assessment: a systematic review

Contact Info

Product

Resources

About