发表机构
Centres of Innovation and Research; KIIT Deemed to be University（创新与研究中心; KIIT大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对QNeRF中空间坐标正弦位置编码扩展性差的问题，提出用多分辨率哈希编码取代其空间坐标正弦位置编码，设计出Hash-QNeRF，实现快速收敛和内存高效，在合成场景有良好训练损失及PSNR表现，且不降低量子电路噪声容限。
AI 中文摘要
神经辐射场（NeRF）彻底改变了新视图合成，但经典实现对高保真渲染计算量很大。QNeRF通过结合幅度嵌入、参数化量子电路（PQCs）、基于奇偶校验的测量和体渲染，证明了在基于门的量子计算机上训练NeRF的可行性。然而，QNeRF依赖于经典正弦位置编码，在场景复杂性和分辨率增加时扩展性差。本文用来自Instant-NGP的多分辨率哈希编码取代正弦位置编码，同时保持视图方向编码等不变。这种混合设计Hash-QNeRF在合成Blender场景中实现最终训练损失0.003534，拟合批次的PSNR约为24.5dB，且噪声弹性实验表明哈希编码不降低量子电路噪声容限。
英文摘要
Neural Radiance Fields (NeRF) have revolutionized novel view synthesis, yet their classical implementations remain computationally intensive for high-fidelity rendering. QNeRF recently demonstrated the feasibility of training NeRF on gate-based quantum computers by combining amplitude embedding, parameterized quantum circuits (PQCs), parity-based measurements, and volumetric rendering. However, QNeRF relies on classical sinusoidal positional encoding for spatial coordinates, which scales poorly with scene complexity and resolution. In this work, we replace the sinusoidal positional encoding for spatial coordinates with the multiresolution hash encoding from Instant-NGP while keeping the view-direction encoding, amplitude MLP, quantum circuit, parity measurement, output scaling, and volumetric rendering pipeline unchanged. This hybrid design, Hash-QNeRF, retains the quantum radiance prediction step while benefiting from the fast convergence and memory efficiency of learnable hash grids. On a synthetic Blender scene, we achieve a final training loss of 0.003534, corresponding to approximately 24.5 dB PSNR on the fitted batch. Noise resilience experiments using Qiskit FakeKyiv and FakeTorino backends yield state fidelities of 0.93 to 0.98, indicating that hash encoding does not degrade the quantum circuit's noise tolerance.
