用专家混合模型提升隐式神经表示的局部建模能力，更快更准更省内存。
Neural Experts: Mixture of Experts for Implicit Neural Representations
- 将专家混合架构引入隐式神经表示，实现分块局部拟合
- 在图像、表面和音频重建中提升精度并降低内存占用
- 新门控网络预训练方法加速收敛，适合高精度重建任务
隐式神经表示（INRs）在图像、形状、音频和视频重建等任务中表现优异，通常通过单个网络对整个域进行全局建模，施加大量全局约束。本文提出一种基于专家混合（MoE）的隐式神经表示方法，能够学习局部分段连续函数，同时自动划分域并局部拟合。将MoE架构融入现有INR框架后，显著提升了速度、精度并降低了内存需求。此外，我们设计了新的门控网络条件化与预训练方法，加快收敛至理想解。在表面重建、图像重建和音频信号重建等多个任务上验证了该方法的有效性，性能优于非MoE基线方法。
原文摘要 · Abstract (English)
Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a single network for the entire domain, imposing many global constraints on a single function. In this paper, we propose a mixture of experts (MoE) implicit neural representation approach that enables learning local piece-wise continuous functions that simultaneously learns to subdivide the domain and fit locally. We show that incorporating a mixture of experts architecture into existing INR formulations provides a boost in speed, accuracy, and memory requirements. Additionally, we introduce novel conditioning and pretraining methods for the gating network that improves convergence to the desired solution. We evaluate the effectiveness of our approach on multiple reconstruction tasks, including surface reconstruction, image reconstruction, and audio signal reconstruction and show improved performance compared to non-MoE methods.
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。