Asynchronous Feedback Network for Perceptual Point Cloud Quality Assessment
Yujie Zhang, Qi Yang, Ziyu Shan, Yiling Xu

TL;DR
This paper introduces AFQ-Net, a novel deep learning model inspired by human visual perception, that effectively captures global and local features for no-reference point cloud quality assessment, outperforming existing methods.
Contribution
The paper proposes a dual-branch asynchronous feedback network with a feedback module, enhancing global-local feature interaction for improved point cloud quality prediction.
Findings
Achieves superior performance on three benchmark datasets.
Outperforms state-of-the-art methods in point cloud quality assessment.
Demonstrates the effectiveness of feedback mechanisms in deep learning models.
Abstract
Recent years have witnessed the success of the deep learning-based technique in research of no-reference point cloud quality assessment (NR-PCQA). For a more accurate quality prediction, many previous studies have attempted to capture global and local features in a bottom-up manner, but ignored the interaction and promotion between them. To solve this problem, we propose a novel asynchronous feedback quality prediction network (AFQ-Net). Motivated by human visual perception mechanisms, AFQ-Net employs a dual-branch structure to deal with global and local features, simulating the left and right hemispheres of the human brain, and constructs a feedback module between them. Specifically, the input point clouds are first fed into a transformer-based global encoder to generate the attention maps that highlight these semantically rich regions, followed by being merged into the global feature.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · Optical measurement and interference techniques · 3D Surveying and Cultural Heritage
MethodsSoftmax · Attention Is All You Need · Convolution
