用低秩方法高效更新神经场，实现小改动的轻量级编码。
Low-Rank Adaptation of Neural Fields
- 采用低秩适应技术，仅调整少量参数即可更新神经场。
- 在图像滤波、几何编辑等任务中实现高效压缩与快速响应。
- 适合需要频繁微调但资源受限的场景，如移动端应用。
视觉数据处理常涉及微小调整或连续变化，如图像滤波、表面平滑和动画生成。尽管传统图形技术（如法线贴图、视频压缩）利用冗余高效编码这些变化，但针对神经场——即视觉或物理函数的神经网络参数化——的小幅度更新仍缺乏关注。本文提出一种基于低秩适应（LoRA）的参数高效更新策略，将源自大语言模型参数高效微调领域的LoRA方法适配至实例特定的神经场，避免使用大型预训练模型，实现轻量级更新。通过图像滤波、几何编辑、视频压缩及基于能量的编辑实验验证，该方法在多种任务中均表现出有效性与通用性。
原文摘要 · Abstract (English)
Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to encode such small changes efficiently, the problem of encoding small changes to neural fields -- neural network parameterizations of visual or physical functions -- has received less attention. We propose a parameter-efficient strategy for updating neural fields using low-rank adaptations (LoRA). LoRA, a method from the parameter-efficient fine-tuning LLM community, encodes small updates to pre-trained models with minimal computational overhead. We adapt LoRA for instance-specific neural fields, avoiding the need for large pre-trained models and yielding lightweight updates. We validate our approach with experiments in image filtering, geometry editing, video compression, and energy-based editing, demonstrating its effectiveness and versatility for representing neural field updates.
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。