Fluid-SDF: Ultra-Lightweight and Editable Implicit Shape Representation via Differentiable Primitives

Researchers introduce Fluid-SDF, a differentiable Constructive Solid Geometry framework that models shapes using explicit geometric primitives with under 100 parameters, achieving comparable or superior intersection-over-union to standard neural baselines while resisting noise and enabling direct user editing without retraining. The method is designed for mobile AI, augmented reality, and resource-constrained embedded environments.

arXiv:2607.18646v1 Announce Type: new Abstract: 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