Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks

TL;DR

This paper introduces a quantum implicit neural representation (QINR) integrated into autoencoders and variational autoencoders, demonstrating improved image reconstruction and generation capabilities, especially in diversity and detail, using hybrid quantum-classical models.

Contribution

The paper presents a novel QINR-based autoencoder and VAE framework that enhances image generation and reconstruction, addressing stability and diversity issues in quantum generative models.

Findings

QINR-VAE produces more diverse images with less data.

Reconstructed images are sharp and detailed.

QINR integration improves model stability and performance.

Abstract

We propose a quantum implicit neural representation (QINR)-based autoencoder (AE) and variational autoencoder (VAE) for image reconstruction and generation tasks. Our purpose is to demonstrate that the QINR in VAEs and AEs can transform information from the latent space into highly rich, periodic, and high-frequency features. Additionally, we aim to show that the QINR-VAE can be more stable than various quantum generative adversarial network (QGAN) models in image generation because it can address the low diversity problem. Our quantum-classical hybrid models consist of a classical convolutional neural network (CNN) encoder and a quantum-based QINR decoder. We train the QINR-AE/VAE with binary cross-entropy with logits (BCEWithLogits) as the reconstruction loss. For the QINR-VAE, we additionally employ Kullback-Leibler divergence for latent regularization with beta/capacity scheduling to prevent posterior collapse. We introduce learnable angle-scaling in data reuploading to address optimization challenges. We test our models on the MNIST, E-MNIST, and Fashion-MNIST datasets to reconstruct and generate images. Our results demonstrate that the QINR structure in VAE can produce a wider variety of images with a small amount of data than various generative models that have been studied. We observe that the generated and reconstructed images from the QINR-VAE/AE are clear with sharp boundaries and details. Overall, we find that the addition of QINR-based quantum layers into the AE/VAE frameworks enhances the performance of reconstruction and generation with a constrained set of parameters.