Affiliation:
1. Shanghai Jiao Tong University, Shanghai, China
2. Nanyang Technological University, Singapore
Abstract
Nowadays, most 3D model quality assessment (3DQA) methods have been aimed at improving accuracy. However, little attention has been paid to the computational cost and inference time required for practical applications. Model-based 3DQA methods extract features directly from the 3D models, which are characterized by their high degree of complexity. As a result, many researchers are inclined towards utilizing projection-based 3DQA methods. Nevertheless, previous projection-based 3DQA methods directly extract features from multi-projections to ensure quality prediction accuracy, which calls for more resource consumption and inevitably leads to inefficiency. Thus in this paper, we address this challenge by proposing a no-reference (NR) projection-based
G
rid
M
ini-patch
S
ampling
3D
Model
Q
uality
A
ssessment (GMS-3DQA)
method. The projection images are rendered from six perpendicular viewpoints of the 3D model to cover sufficient quality information. To reduce redundancy and inference resources, we propose a multi-projection grid mini-patch sampling strategy (MP-GMS), which samples grid mini-patches from the multi-projections and forms the sampled grid mini-patches into one quality mini-patch map (QMM). The Swin-Transformer tiny backbone is then used to extract quality-aware features from the QMMs. The experimental results show that the proposed GMS-3DQA outperforms existing state-of-the-art NR-3DQA methods on the point cloud quality assessment databases for both accuracy and efficiency. The efficiency analysis reveals that the proposed GMS-3DQA requires far less computational resources and inference time than other 3DQA competitors. The code is available at https://github.com/zzc-1998/GMS-3DQA.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference71 articles.
1. No-reference mesh visual quality assessment via ensemble of convolutional neural networks and compact multi-linear pooling
2. Ilyass Abouelaziz Mohammed El Hassouni and Hocine Cherifi. 2016. No-Reference 3D Mesh Quality Assessment Based on Dihedral Angles Model and Support Vector Regression. In Image and Signal Processing. 369–377.
3. I. Abouelaziz, M. E. Hassouni, and H. Cherifi. 2017. A convolutional neural network framework for blind mesh visual quality assessment. In IEEE International Conference on Image Processing. 755–759.
4. Evangelos Alexiou and Touradj Ebrahimi. 2018. Point Cloud Quality Assessment Metric Based on Angular Similarity. In IEEE International Conference on Multimedia and Expo. 1–6.
5. Evangelos Alexiou and Touradj Ebrahimi. 2020. Towards a point cloud structural similarity metric. In IEEE International Conference on Multimedia & Expo Workshops. 1–6.