发表机构
University of California, San Diego (UCSD)（加利福尼亚大学圣地亚哥分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对隐式神经表示在形状建模上的问题，提出Fluid-SDF框架，用可微基元建模，参数少，能抵抗噪声，可直接编辑形状特征，无需重新训练，适合移动AI等资源受限环境。
AI 中文摘要
隐式神经表示（INRs）已成为连续二维形状建模的标准，但存在黑箱不可编辑、易受噪声影响以及参数数量多等问题，严重阻碍在边缘设备上的部署。我们引入了流体符号距离函数（Fluid-SDF），这是一个高度压缩的、可微的构造实体几何（CSG）框架，它使用通过平滑最小函数混合的显式几何基元对形状进行建模。通过用参数化基元引擎取代传统多层感知器（MLP），Fluid-SDF使用严格少于100个参数重建复杂的非凸拓扑，在交并比（mIoU）上与标准神经基线相当或更优。此外，它能抵抗高频数据集噪声，且其显式参数空间允许对局部和全局形状特征进行直接、零样本用户编辑，无需重新训练。通过完全绕过昂贵的设备上梯度更新，它特别适用于移动人工智能、增强现实和资源受限的嵌入式环境。
英文摘要
Implicit Neural Representations (INRs) have become the standard for continuous 2D shape modeling, but they suffer from black-box uneditability, vulnerability to noise, and high parameter counts that severely hinder deployment on edge devices. We introduce Fluid-SDF, a highly compressed, differentiable Constructive Solid Geometry (CSG) framework that models shapes using explicit geometric primitives blended via a smooth minimum function. By replacing traditional multi-layer perceptrons (MLPs) with a parameterized primitive engine, Fluid-SDF reconstructs complex, non-convex topologies using strictly under 100 parameters, achieving comparable or superior intersection-over-union (mIoU) to standard neural baselines. Furthermore, we demonstrate that Fluid-SDF acts as a powerful geometric prior, inherently resisting high-frequency dataset noise where capacity-matched neural networks catastrophically overfit. Finally, unlike standard INRs, Fluid-SDF's explicit parameter space allows for direct, zero-shot user editing of local and global shape features without retraining. By bypassing expensive on-device gradient updates entirely, Fluid-SDF is uniquely suited for mobile AI, augmented reality, and resource-constrained embedded environments
Comments6 pages, 5 figures
