Search papers, labs, and topics across Lattice.
The authors construct a hybrid quantum-classical diffusion framework where the forward noising process is modeled via a Discrete-Time Quantum Walk executed on physical quantum hardware, paired with a classical neural network for reverse denoising. By decoupling the quantum forward walk from parameter-heavy classical learning, the architecture overcomes the severe qubit limits that typically confine quantum machine learning to low-resolution toy datasets. Benchmarked across 2D RGB, grayscale, and 3D medical volumes, the hybrid system matches the generative performance of classical discrete-state diffusion models across standard image quality metrics.
Real quantum hardware can scale past toy benchmarks to high-dimensional 3D medical imaging by restricting physical QPU execution strictly to forward diffusion dynamics.
Quantum Machine Learning is a novel field of research aimed at devising machine learning approaches exploiting principles of quantum mechanics, such as superposition, entanglement and interference. In this context, we present a scalable hybrid Quantum Diffusion Model, and evaluate its use for medical image analysis. Specifically, our method is based on a Discrete-Time Quantum Walk algorithm, executed on a real quantum device, to model the forward dynamics of the diffusion model. For the backward step of the diffusion model, we devise and evaluate a classical learning model, which is used to reversely denoise the data. In contrast with other existing attempts at applying quantum machine learning for image analysis tasks, severely limited by the size of existing quantum devices, our method allows to process real-world large size medical data. In particular, we present results on grayscale and RGB images, as well as 3D volumes of moderate sizes. We benchmark our results by reproducing an alternative classical counterpart model, based on diffusion models on discrete state spaces. By doing so, we compare the generation capabilities of both models in terms of three distinct state-of-the-art metrics in the field of image generation, showing the competitive, promising results of our approach.
