LeafFit: Plant Assets Creation from 3D Gaussian Splatting

TL;DR

LeafFit transforms complex 3D Gaussian Splatting models of plants into lightweight, editable mesh assets by segmenting and fitting leaf templates, enabling efficient storage and real-time deformation suitable for game development workflows.

Contribution

The paper introduces a novel pipeline that converts 3D Gaussian Splatting of plants into editable mesh assets using leaf segmentation, template fitting, and on-the-fly deformation.

Findings

Higher segmentation quality than recent baselines

More accurate leaf deformation results

Significantly reduced data size for assets

Abstract

We propose LeafFit, a pipeline that converts 3D Gaussian Splatting (3DGS) of individual plants into editable, instanced mesh assets. While 3DGS faithfully captures complex foliage, its high memory footprint and lack of mesh topology make it incompatible with traditional game production workflows. We address this by leveraging the repetition of leaf shapes; our method segments leaves from the unstructured 3DGS, with optional user interaction included as a fallback. A representative leaf group is selected and converted into a thin, sharp mesh to serve as a template; this template is then fitted to all other leaves via differentiable Moving Least Squares (MLS) deformation. At runtime, the deformation is evaluated efficiently on-the-fly using a vertex shader to minimize storage requirements. Experiments demonstrate that LeafFit achieves higher segmentation quality and deformation accuracy than recent baselines while significantly reducing data size and enabling parameter-level editing.