用量子方法提升隐式神经表示的细节还原能力
QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representations
- 基于量子傅里叶高斯网络，通过抑制低频成分平衡频谱
- 参数极少却超越现有最先进模型，硬件噪声下仍接近SIREN精度
- 适合对高保真图像重建感兴趣的量子机器学习研究者
隐式神经表示在诸多应用中展现出潜力，但准确重构图像或实现清晰细节的超分辨率仍具挑战。本文提出量子傅里叶高斯网络（QFGN），一种基于量子的机器学习模型，用于更优的信号表示。通过惩罚低频分量，均衡频率谱，提升了量子电路的表达能力。结果表明，仅用极少参数，QFGN即超越当前最先进（SOTA）模型。尽管存在硬件噪声，其性能仍可媲美SIREN，彰显了量子机器学习在此领域的应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。