Pointpca+: A Full-Reference Point Cloud Quality Assessment Metric with Pca-Based Features

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

---

Quality Assessment and Modeling for MPEG V-PCC Volumetric Video

Published: April 4, 2024

Volumetric video, which is typically represented by 3D point clouds, requires efficient cloud compression (PCC) technologies for practical storage and transmission. Particularly, developed the Moving Picture Experts Group (MPEG), video-based PCC (V-PCC) converts clouds into 2D image maps compresses them with video codecs, showing excellent performance. However, understanding impact of on perceptual quality volumetric videos, consist both geometry texture components, remains challenging. In this study, we propose a experience (QoE) model to predict subjective respect level texture, quantifying quality. To best our knowledge, study first accurately V-PCC-encoded videos. The QoE built based assessment dataset, VOLVQAD, collected us. We further evaluate vsenseVVDB2 was from diverse settings, validate its robustness generalization ability. Both evaluations demonstrate effectiveness in various scenarios. This makes valuable contribution factors that influence proposed also holds potential other applications, such as adaptive bitrate allocation.

Language: Английский

---

Perceptual Impact of Facial Quality in MPEG V-PCC-encoded Volumetric Videos

Published: April 4, 2024

Volumetric video, a technique used in augmented reality (AR) and virtual (VR) applications, presents unique challenges rendering compression. To enable efficient compression, video-based point cloud compression (V-PCC) techniques have been introduced by the Moving Picture Experts Group (MPEG). Given interaction nature of volumetric videos, it is important to understand impact user behavior for optimizations video transmission In this study, we investigate influence face quality avatars on users' viewing experience MPEG V-PCC-encoded videos. We conducted subjective assessment study using Degradation Category Rating (DCR) method, manipulating facial controlling level V-PCC. Our analysis reveals significant role influencing overall perceptual The generated videos data made public at https://github.com/nus-vv-streams/facial-quality support further research.

Language: Английский

---

Enhancing Immersive Experiences through 3D Point Cloud Analysis: A Novel Framework for Applying 2D Visual Saliency Models to 3D Point Clouds

Published: June 18, 2024

Language: Английский

---