研究人员开发了一种使用正弦循环来增强隐式神经表示（INR）的新方法。这种迭代方法丰富了潜在表示的频谱支持，从而在图像超分辨率、NeRF和符号距离函数（SDF）估计等任务中提高了性能。与现有的前馈INR相比，所提出的架构以更少的参数和优化步骤实现了更高的保真度。 AI
影响 这项研究可能为各种计算机视觉和3D表示任务带来更高效、更高保真的模型。
排序理由 该集群包含两篇关于隐式神经表示新方法的学术论文预印本。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spectral account of how recurrent unrolling enriches …
We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spectral account of how recurrent unrolling enriches …
arXiv:2607.21485v1 Announce Type: new Abstract: We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spect…