Activating Frequency and ViT for 3D Point Cloud Quality Assessment without Reference
This work addresses the need for efficient quality assessment in 3D point cloud compression for multimedia transmission, representing an incremental improvement in a domain-specific area.
The paper tackles the problem of assessing the quality of compressed 3D point clouds without a reference, proposing a no-reference metric that integrates frequency magnitudes to indicate spatial degradation and uses a hybrid deep model combining Deformable Convolutional Networks and Vision Transformers. The results show that this approach outperforms state-of-the-art no-reference methods and even some full-reference methods on the PointXR dataset.
Deep learning-based quality assessments have significantly enhanced perceptual multimedia quality assessment, however it is still in the early stages for 3D visual data such as 3D point clouds (PCs). Due to the high volume of 3D-PCs, such quantities are frequently compressed for transmission and viewing, which may affect perceived quality. Therefore, we propose no-reference quality metric of a given 3D-PC. Comparing to existing methods that mostly focus on geometry or color aspects, we propose integrating frequency magnitudes as indicator of spatial degradation patterns caused by the compression. To map the input attributes to quality score, we use a light-weight hybrid deep model; combined of Deformable Convolutional Network (DCN) and Vision Transformers (ViT). Experiments are carried out on ICIP20 [1], PointXR [2] dataset, and a new big dataset called BASICS [3]. The results show that our approach outperforms state-of-the-art NR-PCQA measures and even some FR-PCQA on PointXR. The implementation code can be found at: https://github.com/o-messai/3D-PCQA