mlsanityData to 14 Oct 2026

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

arXiv 2311.05604 ↗First posted 9 Nov 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 76 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

42 of 76 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  3. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  4. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  5. 2018Supervised learning with quantum enhanced feature spacescited by 665
  6. 2018Barren plateaus in quantum neural network training landscapescited by 630
  7. 2020The power of quantum neural networkscited by 379
  8. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  9. 2019Transfer learning in hybrid classical-quantum neural networkscited by 114
  10. 2021Information-theoretic bounds on quantum advantage in machine learningcited by 96
  11. 2021Quantum machine learning beyond kernel methodscited by 92
  12. 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 90
30 more
  1. 2017Variational Autoencoders for Deforming 3D Mesh Modelscited by 70
  2. 2022Theory for Equivariant Quantum Neural Networkscited by 62
  3. 2020Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernelscited by 53
  4. 2022Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networkscited by 52
  5. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  6. 2022Representation Theory for Geometric Quantum Machine Learningcited by 40
  7. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39
  8. 2021On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classificationcited by 33
  9. 2021Quantum Permutation Synchronizationcited by 32
  10. 2021Q-Match: Iterative Shape Matching via Quantum Annealingcited by 27
  11. 2019A Quantum Computational Approach to Correspondence Problems on Point Setscited by 23
  12. 2022Adiabatic Quantum Computing for Multi Object Trackingcited by 22
  13. 2021Hybrid Quantum-Classical Graph Convolutional Networkcited by 21
  14. 2021Quantum Neural Networks: Concepts, Applications, and Challengescited by 21
  15. 2019DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objectscited by 20
  16. 2022A Hybrid Quantum-Classical Algorithm for Robust Fittingcited by 16
  17. 2022Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learningcited by 16
  18. 2022Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learningcited by 16
  19. 2021Quantum-Classical Hybrid Machine Learning for Image Classification (ICCAD Special Session Paper)cited by 14
  20. 2023Quantum Multi-Model Fittingcited by 12
  21. 2023CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapescited by 11
  22. 2020Denoising quantum states with Quantum Autoencoders -- Theory and Applicationscited by 8
  23. 2021Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizescited by 8
  24. 2022Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimizationcited by 8
  25. 2022Quantum neural network autoencoder and classifier applied to an industrial case studycited by 8
  26. 2017Mesh-based Autoencoders for Localized Deformation Component Analysiscited by 7
  27. 2021Scalable Variational Quantum Circuits for Autoencoder-based Drug Discoverycited by 6
  28. 2022Quantum artificial vision for defect detection in manufacturingcited by 3
  29. 2022QuAnt: Quantum Annealing with Learnt Couplingscited by 3
  30. 2022DeepQMLP: A Scalable Quantum-Classical Hybrid DeepNeural Network Architecture for Classificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Quantum Visual Fields with Neural Amplitude Encodingcited by 6
  2. 2025Quantum-enhanced Computer Vision: Going Beyond Classical Algorithmscited by 5
  3. 2026Quantum Implicit Neural Representations for Novel View Synthesiscited by 1
  4. 2026Universality of Many-body Projected Ensemble for Learning Quantum Data Distributioncited by 0
  5. 2026Latent-Conditioned Parameterized Quantum Circuits as Universal Approximators for Distributions over Quantum Statescited by 0