QCTKD-PU: Quantum Convolutional Transformer with Knowledge Distillation for Efficient and Robust Point Cloud Upsampling
Authors:
- 5 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 758-763
Abstract
Point cloud upsampling is crucial for high-fidelity 3D reconstruction in real-time applications such as autonomous systems. Existing methods based on CNNs or Transformers face three limitations: (1) prohibitive computational complexity hindering real-time deployment, (2) insufficient modeling of multi-scale geometric dependencies in sparse data, (3) sensitivity to noise and outliers. To address these challenges, we propose QCTKD-PU, a framework integrating Quantum Convolutional Transformers (QCT) and Knowledge Distillation (KD) for Point cloud Upsampling. The QCT leverages quantum superposition and self-attention to encode high-dimensional features, enabling efficient multi-scale point interaction learning. Simultaneously, KD transfers knowledge from a teacher model to a lightweight student network, reducing computational costs while maintaining accuracy. Experiments on benchmark datasets demonstrate superior performance in geometric accuracy and noise robustness compared to state-of-the-art methods. This work pioneers the synergy of quantum computing and lightweight learning for resource-constrained 3D vision tasks, while the student model achieves real-time and compact deployment, offering a practical solution for collaborative edge systems.Keywords
This publication has 32 references indexed in Scilit:
- Enforcing exact permutation and rotational symmetries in the application of quantum neural networks on point cloud datasetsPhysical Review Research, 2024
- Permutation invariant encodings for quantum machine learning with point cloud dataQuantum Machine Intelligence, 2024
- Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptionsInformation Sciences, 2023
- Stereoscopic scalable quantum convolutional neural networksNeural Networks, 2023
- Point Cloud Upsampling via Cascaded Refinement Network2023
- PU-Transformer: Point Cloud Upsampling Transformer2023
- PUGeo-Net: A Geometry-Centric Network for 3D Point Cloud Upsampling2020
- Quantum convolutional neural networksNature Physics, 2019
- Patch-Based Progressive 3D Point Set Upsampling2019
- PU-Net: Point Cloud Upsampling Network2018