arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12839cs.CVcs.LGeess.IVeess.SP
收藏

3D点云的深度感知度量

A deep perceptual metric for 3D point clouds

Université Paris-Saclay(巴黎-萨克雷大学);CNRS(法国国家科学研究中心);CentraleSupélec(中央高等电力学院);Université d’Orléans(奥尔良大学)

Maurice Quach, Aladine Chetouani, Giuseppe Valenzise, Frederic Dufaux

摘要:

点云对于存储和传输3D内容至关重要。由于点云可能需要大量数据,因此点云压缩对于实际使用至关重要。最近,已经探索了基于深度神经网络的点云几何压缩方法。在本文中,我们评估的能力来预测感知质量的典型的基于体素的损失函数训练这些网络。我们发现,常用的焦点损失和加权二进制交叉熵与人类感知的相关性很差。因此,我们提出了一个三维点云的感知损失函数,它优于ICIP 2020主观数据集上现有的损失函数。此外,我们提出了一种新的截断距离场体素网格表示,并发现它导致稀疏的潜在空间和损失函数,更相关的感知视觉质量相比,一个二进制表示。源代码可在https://github.com/mauriceqch/2021_pc_perceptual_loss上获得。

英文摘要:

Point clouds are essential for storage and transmission of 3D content. As they can entail significant volumes of data, point cloud compression is crucial for practical usage. Recently, point cloud geometry compression approaches based on deep neural networks have been explored. In this paper, we evaluate the ability to predict perceptual quality of typical voxel-based loss functions employed to train these networks. We find that the commonly used focal loss and weighted binary cross entropy are poorly correlated with human perception. We thus propose a perceptual loss function for 3D point clouds which outperforms existing loss functions on the ICIP2020 subjective dataset. In addition, we propose a novel truncated distance field voxel grid representation and find that it leads to sparser latent spaces and loss functions that are more correlated with perceived visual quality compared to a binary representation. The source code is available at https://github.com/mauriceqch/2021_pc_perceptual_loss.

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。

↑