NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement

Yang Yang1, Dongni Mao1, Hiroaki Santo1, Yasuyuki Matsushita1,2, Fumio Okura1,
1The university of Osaka, 2Microsoft Research Asia - Tokyo
Paper arXiv Video Code Data
Teaser

NeuraLeaf represents shapes of various leaf species and natural 3D deformation. Our model represents the leaves' flattened shape and their 3D deformation in disentangled latent space

Abstract

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.

Video

BibTeX

@article{xxxx,
  author    = {Yang, Yang and Dongni, Mao and Hiroaki, Santo and Yasuyuki, Matsushita and Fumio, Okura},
  title     = {NeuraLeaf: Neural Parametric Leaf Modelswith Shape and Deformation Disentanglement},
  journal   = {ICCV},
  year      = {2025},
}