Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-Relevance Degradation Description
- 4 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 71 (2) , 616-630
Abstract
The visual quality of point clouds plays a crucial role in the development and broadcasting of immersive media. Therefore, investigating point cloud quality assessment (PCQA) is instrumental in facilitating immersive media applications, including virtual reality and augmented reality applications. Considering reference point clouds are not available in many cases, no-reference (NR) metrics have become a research hotspot. Existing NR methods suffer from difficult training. To address this shortcoming, we propose a novel NR-PCQA method, Point Cloud Quality Assessment via Domain-relevance Degradation Description (D3-PCQA). First, we demonstrate our model’s interpretability by deriving the function of each module using a kernelized ridge regression model. Specifically, quality assessment can be characterized as a leap from the scattered perceptual domain (reflecting subjective perception) to the ordered quality domain (reflecting mean opinion score). Second, to reduce the significant domain discrepancy, we establish an intermediate domain, the description domain, based on insights from the human visual system (HVS), by considering the domain relevance among samples located in the perception domain and learning a structured latent space. The anchor features derived from the learned latent space are generated as cross-domain auxiliary information to promote domain transformation. Furthermore, the newly established description domain decomposes the NR-PCQA problem into two relevant stages. These stages include a classification stage that gives the degradation descriptions to point clouds and a regression stage to determine the confidence degrees of descriptions, providing a semantic explanation for the predicted quality scores. Experimental results demonstrate that D3-PCQA exhibits robust performance and outstanding generalization on several publicly available datasets.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62371290)
- National Key Research and Development Program of China (2024YFB2907204)
- Fundamental Research Funds for the Central Universities
- Science and Technology Commission of Shanghai Municipality (22DZ2229005)
This publication has 60 references indexed in Scilit:
- REQA: Coarse-to-fine assessment of image quality to alleviate the range effectJournal of Visual Communication and Image Representation, 2024
- Joint Geometry and Color Projection-Based Point Cloud Quality MetricIEEE Access, 2022
- A morphing-Based 3D point cloud reconstruction framework for medical image processingComputer Methods and Programs in Biomedicine, 2020
- A comprehensive study of the rate-distortion performance in MPEG point cloud compressionAPSIPA Transactions on Signal and Information Processing, 2019
- A Survey of DNN Methods for Blind Image Quality AssessmentIEEE Access, 2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- A natural approach to studying visionNature Neuroscience, 2005
- Multiscale structural similarity for image quality assessment2004
- A Generalized Representer Theorem2001
- Computing a nearest symmetric positive semidefinite matrixLinear Algebra and its Applications, 1988