English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the rapid development of 3D vision, point cloud has become anincreasingly popular 3D visual media content. Due to the irregular structure,point cloud has posed novel challenges to the related research, such ascompression, transmission, rendering and quality assessment. In these latestresearches, point cloud quality assessment (PCQA) has attracted wide attentiondue to its significant role in guiding practical applications, especially inmany cases where the reference point cloud is unavailable. However, currentno-reference metrics which based on prevalent deep neural network have apparentdisadvantages. For example, to adapt to the irregular structure of point cloud,they require preprocessing such as voxelization and projection that introduceextra distortions, and the applied grid-kernel networks, such as ConvolutionalNeural Networks, fail to extract effective distortion-related features.Besides, they rarely consider the various distortion patterns and thephilosophy that PCQA should exhibit shifting, scaling, and rotationalinvariance. In this paper, we propose a novel no-reference PCQA metric namedthe Graph convolutional PCQA network (GPA-Net). To extract effective featuresfor PCQA, we propose a new graph convolution kernel, i.e., GPAConv, whichattentively captures the perturbation of structure and texture. Then, wepropose the multi-task framework consisting of one main task (qualityregression) and two auxiliary tasks (distortion type and degree predictions).Finally, we propose a coordinate normalization module to stabilize the resultsof GPAConv under shift, scale and rotation transformations. Experimentalresults on two independent databases show that GPA-Net achieves the bestperformance compared to the state-of-the-art no-reference PCQA metrics, evenbetter than some full-reference metrics in some cases.

GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network