发表机构
Department of Electrical Engineering, Korea University; Graduate School of Artificial Intelligence, UNIST（韩国大学电气工程系; 蔚山国立科学技术院人工智能研究生院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究将正弦循环用于INRs谐波频谱丰富，通过共享正弦块迭代优化潜在表示，经实验验证其频谱行为，在图像和3D表示任务中表现出色，能以少参数和步骤实现高保真，还可迁移至多种相关任务。
AI 中文摘要
我们研究正弦循环作为隐式神经表示（INRs）中谐波频谱丰富的迭代机制。分析表明正弦激活会产生谐波线谱，解释了循环展开如何丰富有效频谱支持。我们通过共享正弦块实现这一原理，迭代优化潜在表示。通过与前馈INRs、非正弦循环变体和平衡式正弦模型对比验证频谱行为。在图像和3D表示任务中评估该架构，在RGB图像基准测试中，以更少参数和优化步骤实现更高保真度，并能很好地迁移到超分辨率、NeRF和SDF任务。
英文摘要
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 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.
CommentsAccepted to ECCV 2026 (Poster)
