用傅里叶域稀疏学习，让连续核模型更快更省内存
Scaling Continuous Kernels with Sparse Fourier Domain Learning
- 在傅里叶域做稀疏学习，提升连续核的计算效率
- 计算量和内存占用降低90%以上，支持更大规模模型
- 利用吉布斯现象缓解高频细节捕捉难题，适合高保真任务
我们解决了连续核表示学习中的三大挑战：计算效率、参数效率与频谱偏差。尽管连续核展现出巨大潜力，但其实际应用常受限于高计算与内存开销。此外，这些方法易受频谱偏差影响，难以捕捉高频细节。为此，我们提出一种新颖方法，利用傅里叶域的稀疏学习。该方法显著提升了连续核的可扩展性，大幅降低计算与内存需求，并通过利用吉布斯现象缓解频谱偏差。实验表明，在相同精度下，该方法将计算量与内存占用减少超过90%，且在NeRF、SIREN等基准上实现更优的高频重建性能。
原文摘要 · Abstract (English)
We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often limited by high computational and memory demands. Additionally, these methods are prone to spectral bias, which impedes their ability to capture high-frequency details. To overcome these limitations, we propose a novel approach that leverages sparse learning in the Fourier domain. Our method enables the efficient scaling of continuous kernels, drastically reduces computational and memory requirements, and mitigates spectral bias by exploiting the Gibbs phenomenon.
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。