Fully Quantum Auto-Encoding of 3D Shapes
Lakshika Rathi (Indian Institute of Technology Delhi), Edith Tretschk (Max-Planck-Institut für Informatik),* Christian Theobalt (MPI Informatik), Rishabh Dabral (IIT Bombay), Vladislav Golyanik (MPI for Informatics)
The 34th British Machine Vision Conference
Abstract
Existing methods for learning 3D shape representations are deep neural networks on classical hardware. Quantum machine learning (QML) architectures---despite their recognized 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 shapes. 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 shapes to produce their compressed representations. Along with finding a suitable architecture, the core challenges in designing such a fully-quantum model include 3D data normalization and parameter optimization, 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.Citation
@inproceedings{Rathi_2023_BMVC,
author = {Lakshika Rathi and Edith Tretschk and Christian Theobalt and Rishabh Dabral and Vladislav Golyanik},
title = {Fully Quantum Auto-Encoding of 3D Shapes},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0382.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by