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

Abstract

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.

Plant phenotyping relevance

植物の多視点画像から枝構造と葉インスタンスを再構成・抽出する手法を開発しており、植物フェノタイピングへの適用と形態情報の抽出が中心的な技術貢献である。

Code and data availability

The paper introduces the GaussianPlant dataset (10 plants, multi-view images, ground-truth branch/leaf annotations) and states code will be released, but only as a future promise ('will be made publicly available') with no public URL or deposit identifier. The only URLs present (Metashape, Blender) are third-party tool

No evidence-backed public reproduction asset is currently recorded.