Search papers, labs, and topics across Lattice.
Fluid-SDF introduces a novel Constructive Solid Geometry framework that utilizes a differentiable primitive engine to model complex shapes with under 100 parameters, significantly reducing the computational burden associated with traditional Implicit Neural Representations. This method not only achieves competitive intersection-over-union scores compared to existing neural baselines but also demonstrates resilience to high-frequency noise, which typically leads to overfitting in capacity-matched networks. Importantly, Fluid-SDF enables direct user editing of shape features without the need for retraining, making it particularly advantageous for deployment in mobile and resource-constrained environments.
Achieving shape modeling with under 100 parameters while allowing for zero-shot user editing could revolutionize how we deploy AI in mobile and AR applications.
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
