用正弦循环结构提升隐式神经表示的精度与效率。
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
- 采用共享正弦模块迭代优化潜在表征，实现频谱增强。
- 参数更少、优化步数更少，图像重建质量更高。
- 适合图像生成、超分辨率、3D建模等任务，迁移性强。
我们研究正弦递归作为隐式神经表示（INRs）中谐波频谱增强的迭代机制。分析表明，正弦激活函数产生谐波线谱，为递归展开如何扩展有效频谱支持提供了频谱解释。我们通过一个共享正弦块实现该原理，该块迭代细化潜在表征。我们在前馈INRs、非正弦递归变体和平衡型正弦模型上实证验证了其频谱行为。此外，在图像与3D表示任务中评估所提架构：在RGB图像基准上，本方法以更少参数和更少优化步数达到更高保真度，并在超分辨率、NeRF和SDF任务中表现出良好迁移性。
原文摘要 · Abstract (English)
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 the effective spectral support. We realize this principle with a shared sinusoidal block that iteratively refines the latent representation. We empirically validate the resulting spectral behavior against feed-forward INRs, non-sinusoidal recurrent variants, and equilibrium-style sinusoidal models. Complementing this analysis, we evaluate the proposed architecture across image and 3D representation tasks. On RGB image benchmarks, our method achieves higher fidelity than feed-forward baselines with fewer parameters and fewer optimization steps, and it further transfers favorably to super-resolution, NeRF, and SDF tasks.
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。