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 2311.05604cs.CV
收藏

3D-QAE:三维点云的完全量子自编码

3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds

Indian Institute of Technology Delhi(印度理工学院德里分校);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Lakshika Rathi, Edith Tretschk, Christian Theobalt, Rishabh Dabral, Vladislav Golyanik

AI总结:

本文首次提出完全量子自编码器3D-QAE用于三维点云压缩,解决数据归一化与参数优化挑战,实验证明其优于经典基线,开辟三维视觉量子研究方向。

摘要:

现有的三维表示学习方法是在经典硬件上训练和测试的深度神经网络。量子机器学习架构,尽管在速度和表示能力方面具有理论上的优势,但迄今为止尚未被考虑用于此问题,也未用于涉及三维数据的任务。因此,本文首次提出了用于三维点云的量子自编码器。我们的3D-QAE方法完全量子化,即其所有数据处理组件均专为量子硬件设计。该方法在三维点云集合上进行训练,以生成其压缩表示。在设计这种完全量子模型时,除了寻找合适的架构外,核心挑战还包括三维数据归一化和参数优化,我们为这两项任务提出了解决方案。在模拟的基于门的量子硬件上的实验表明,我们的方法优于简单的经典基线,为三维计算机视觉的新研究方向铺平了道路。源代码可在https://4dqv.mpi-inf.mpg.de/QAE3D/获取。

英文摘要:

Existing methods for learning 3D representations are deep neural networks trained and tested on classical hardware. Quantum machine learning architectures, despite their theoretically predicted advantages in terms of speed and the representational capacity, have so far not been considered for this problem nor for tasks involving 3D data in general. This paper thus introduces the first quantum auto-encoder for 3D point clouds. Our 3D-QAE approach is fully quantum, i.e. all its data processing components are designed for quantum hardware. It is trained on collections of 3D point clouds to produce their compressed representations. Along with finding a suitable architecture, the core challenges in designing such a fully quantum model include 3D data normalisation and parameter optimisation, and we propose solutions for both these tasks. Experiments on simulated gate-based quantum hardware demonstrate that our method outperforms simple classical baselines, paving the way for a new research direction in 3D computer vision. The source code is available at https://4dqv.mpi-inf.mpg.de/QAE3D/.

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。

↑