QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations
This work addresses the problem of enhancing signal representation fidelity for applications like image processing, though it appears incremental as it builds on existing quantum and neural representation methods.
The paper tackles the challenge of achieving high-fidelity reconstructions in implicit neural representations, such as for image super-resolution, by introducing QFGN, a quantum-based model that balances frequency spectra to improve expressivity; it reports that QFGN outperforms SOTA models with minimal parameters and achieves accuracy comparable to SIREN despite hardware noise.
Implicit neural representations have shown potential in various applications. However, accurately reconstructing the image or providing clear details via image super-resolution remains challenging. This paper introduces Quantum Fourier Gaussian Network (QFGN), a quantum-based machine learning model for better signal representations. The frequency spectrum is well balanced by penalizing the low-frequency components, leading to the improved expressivity of quantum circuits. The results demonstrate that with minimal parameters, QFGN outperforms the current state-of-the-art (SOTA) models. Despite noise on hardware, the model achieves accuracy comparable to that of SIREN, highlighting the potential applications of quantum machine learning in this field.