NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
This addresses the challenge of creating realistic 3D leaf models for agriculture and computer graphics, representing an incremental advance by adapting neural parametric methods from humans/animals to plants.
The paper tackles the problem of modeling 3D leaves for plant applications by introducing NeuraLeaf, a neural parametric model that disentangles leaf geometry into 2D base shapes and 3D deformations, resulting in accurate fitting to 3D observations such as depth maps and point clouds.
We develop a neural parametric model for 3D leaves for plant modeling and reconstruction that are essential for agriculture and computer graphics. While neural parametric models are actively studied for humans and animals, plant leaves present unique challenges due to their diverse shapes and flexible deformation. To this problem, we introduce a neural parametric model for leaves, NeuraLeaf. Capitalizing on the fact that flattened leaf shapes can be approximated as a 2D plane, NeuraLeaf disentangles the leaves' geometry into their 2D base shapes and 3D deformations. This representation allows learning from rich sources of 2D leaf image datasets for the base shapes, and also has the advantage of simultaneously learning textures aligned with the geometry. To model the 3D deformation, we propose a novel skeleton-free skinning model and create a newly captured 3D leaf dataset called DeformLeaf. We show that NeuraLeaf successfully generates a wide range of leaf shapes with deformation, resulting in accurate model fitting to 3D observations like depth maps and point clouds. Our implementation and dataset are available at https://neuraleaf-yang.github.io/.