解决神经场持续学习的遗忘与慢收敛问题，提升重建速度与质量。
Meta-Continual Learning of Neural Fields
- 采用模块化结构+基于优化的元学习策略
- 在6个数据集上实现更快收敛与更高质量重建
- 适合需要快速适应新场景的神经辐射场应用
神经场（Neural Fields, NF）已成为复杂数据表示的通用框架。本文提出新的问题设定——元持续学习神经场（Meta-Continual Learning of Neural Fields, MCL-NF），并引入一种结合模块化架构与基于优化的元学习的新策略。针对现有神经场持续学习方法存在的灾难性遗忘和收敛缓慢问题，该策略实现了高质量重建与显著提升的学习速度。我们进一步提出针对神经辐射场的费雪信息最大化损失（FIM-NeRF），在样本层面最大化信息增益，以增强学习泛化能力，并提供了收敛保证与泛化界。我们在图像、音频、视频重建及视角合成任务上，在六个不同数据集上进行了广泛评估，结果表明本方法在重建质量和速度方面均优于现有MCL和CL-NF方法。特别地，本方法可在参数需求减少的情况下，实现城市尺度NeRF渲染的快速适应。代码已公开于https://github.com/seungyoon-woo/mcl-nf。
原文摘要 · Abstract (English)
Neural Fields (NF) have gained prominence as a versatile framework for complex data representation. This work unveils a new problem setting termed \emph{Meta-Continual Learning of Neural Fields} (MCL-NF) and introduces a novel strategy that employs a modular architecture combined with optimization-based meta-learning. Focused on overcoming the limitations of existing methods for continual learning of neural fields, such as catastrophic forgetting and slow convergence, our strategy achieves high-quality reconstruction with significantly improved learning speed. We further introduce Fisher Information Maximization loss for neural radiance fields (FIM-NeRF), which maximizes information gains at the sample level to enhance learning generalization, with proved convergence guarantee and generalization bound. We perform extensive evaluations across image, audio, video reconstruction, and view synthesis tasks on six diverse datasets, demonstrating our method's superiority in reconstruction quality and speed over existing MCL and CL-NF approaches. Notably, our approach attains rapid adaptation of neural fields for city-scale NeRF rendering with reduced parameter requirement. Code is available at https://github.com/seungyoon-woo/mcl-nf.
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。