QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909595614576640 |
|---|---|
| author | Jin, Hongni Singh, Gurinder Merz Jr, Kenneth M. |
| author_facet | Jin, Hongni Singh, Gurinder Merz Jr, Kenneth M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations Jin, Hongni Singh, Gurinder Merz Jr, Kenneth M. Quantum Physics Machine Learning 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. |
| title | QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2504.19053 |