GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yang, Shinoda, Risa, Santo, Hiroaki, Okura, Fumio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918249753477120
author Yang, Yang
Shinoda, Risa
Santo, Hiroaki
Okura, Fumio
author_facet Yang, Yang
Shinoda, Risa
Santo, Hiroaki
Okura, Fumio
contents We present a method for jointly recovering the appearance and internal structure of botanical plants from multi-view images based on 3D Gaussian Splatting (3DGS). While 3DGS exhibits robust reconstruction of scene appearance for novel-view synthesis, it lacks structural representations underlying those appearances (e.g., branching patterns of plants), which limits its applicability to tasks such as plant phenotyping. To achieve both high-fidelity appearance and structural reconstruction, we introduce GaussianPlant, a hierarchical 3DGS representation, which disentangles structure and appearance. Specifically, we employ structure primitives (StPs) to explicitly represent branch and leaf geometry, and appearance primitives (ApPs) to the plants' appearance using 3D Gaussians. StPs represent a simplified structure of the plant, i.e., modeling branches as cylinders and leaves as disks. To accurately distinguish the branches and leaves, StP's attributes (i.e., branches or leaves) are optimized in a self-organized manner. ApPs are bound to each StP to represent the appearance of branches or leaves as in conventional 3DGS. StPs and ApPs are jointly optimized using a re-rendering loss on the input multi-view images, as well as the gradient flow from ApP to StP using the binding correspondence information. We conduct experiments to qualitatively evaluate the reconstruction accuracy of both appearance and structure, as well as real-world experiments to qualitatively validate the practical performance. Experiments show that the GaussianPlant achieves both high-fidelity appearance reconstruction via ApPs and accurate structural reconstruction via StPs, enabling the extraction of branch structure and leaf instances.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14087
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants
Yang, Yang
Shinoda, Risa
Santo, Hiroaki
Okura, Fumio
Computer Vision and Pattern Recognition
We present a method for jointly recovering the appearance and internal structure of botanical plants from multi-view images based on 3D Gaussian Splatting (3DGS). While 3DGS exhibits robust reconstruction of scene appearance for novel-view synthesis, it lacks structural representations underlying those appearances (e.g., branching patterns of plants), which limits its applicability to tasks such as plant phenotyping. To achieve both high-fidelity appearance and structural reconstruction, we introduce GaussianPlant, a hierarchical 3DGS representation, which disentangles structure and appearance. Specifically, we employ structure primitives (StPs) to explicitly represent branch and leaf geometry, and appearance primitives (ApPs) to the plants' appearance using 3D Gaussians. StPs represent a simplified structure of the plant, i.e., modeling branches as cylinders and leaves as disks. To accurately distinguish the branches and leaves, StP's attributes (i.e., branches or leaves) are optimized in a self-organized manner. ApPs are bound to each StP to represent the appearance of branches or leaves as in conventional 3DGS. StPs and ApPs are jointly optimized using a re-rendering loss on the input multi-view images, as well as the gradient flow from ApP to StP using the binding correspondence information. We conduct experiments to qualitatively evaluate the reconstruction accuracy of both appearance and structure, as well as real-world experiments to qualitatively validate the practical performance. Experiments show that the GaussianPlant achieves both high-fidelity appearance reconstruction via ApPs and accurate structural reconstruction via StPs, enabling the extraction of branch structure and leaf instances.
title GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14087