arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.01205cs.MMcs.GR
收藏

基于成对秩学习的无参考点云几何质量评价

No-reference Point Cloud Geometry Quality Assessment Based on Pairwise Rank Learning

Zhiyong Su, Chao Chu, Long Chen, Yong Li, Weiqing Li

摘要:

点云的客观几何质量评估对于评估各种基于点云的解决方案的性能至关重要,例如去噪,简化,重建和水印。现有的点云质量评估(PCQA)方法致力于为扭曲的点云分配绝对质量分数。他们的表现在很大程度上依赖于训练的主观地面实况分数的质量和数量,这是具有挑战性的收集,并已被证明是不精确的,有偏见的,和不一致的。此外,大多数现有的客观几何质量评估方法是通过完全参考传统度量进行的。到目前为止,基于点的无参考几何唯一的质量评估技术尚未被研究。本文介绍了PRL-GQA,第一个成对的学习框架,无参考几何只有质量评估的点云,尽我们所知。所提出的PRL-GQA框架采用了一种连体式的深度架构,该架构将一对点云作为输入,并输出它们的排名顺序。每个连体架构分支是一个几何质量评估网络(GQANet),旨在提取多尺度质量感知几何特征,并输出输入点云的质量指数。然后,基于预测的质量指标,引入成对排序学习模块对退化点云的相对质量进行排序,实验结果验证了该框架的有效性。此外,结果还表明,微调无参考GQANet执行竞争力相比,现有的全参考几何质量评估指标。

英文摘要:

Objective geometry quality assessment of point clouds is essential to evaluate the performance of a wide range of point cloud-based solutions, such as denoising, simplification, reconstruction, and watermarking. Existing point cloud quality assessment (PCQA) methods dedicate to assigning absolute quality scores to distorted point clouds. Their performance is strongly reliant on the quality and quantity of subjective ground-truth scores for training, which are challenging to gather and have been shown to be imprecise, biased, and inconsistent. Furthermore, the majority of existing objective geometry quality assessment approaches are carried out by full-reference traditional metrics. So far, point-based no-reference geometry-only quality assessment techniques have not yet been investigated. This paper presents PRL-GQA, the first pairwise learning framework for no-reference geometry-only quality assessment of point clouds, to the best of our knowledge. The proposed PRL-GQA framework employs a siamese deep architecture, which takes as input a pair of point clouds and outputs their rank order. Each siamese architecture branch is a geometry quality assessment network (GQANet), which is designed to extract multi-scale quality-aware geometric features and output a quality index for the input point cloud. Then, based on the predicted quality indexes, a pairwise rank learning module is introduced to rank the relative quality of a pair of degraded point clouds.Extensive experiments demonstrate the effectiveness of the proposed PRL-GQA framework. Furthermore, the results also show that the fine-tuned no-reference GQANet performs competitively when compared to existing full-reference geometry quality assessment metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑