# Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods

arXiv: https://arxiv.org/abs/2012.11489 · HTML: https://mlsanity.com/paper/2012.11489/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage](https://mlsanity.com/paper/2206.13082/) (2022)
- [PLANesT-3D: A new annotated dataset for segmentation of 3D plant point clouds](https://mlsanity.com/paper/2407.21150/) (2024)
- [Learning to Infer Parameterized Representations of Plants from 3D Scans](https://mlsanity.com/paper/2505.22337/) (2025)
- [Using t-distributed stochastic neighbor embedding for visualization and segmentation of 3D point clouds of plants](https://mlsanity.com/paper/2302.03442/) (2023)
- [Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gap](https://mlsanity.com/paper/2509.06329/) (2025)

## Abstract (arXiv)

Segmentation of structural parts of 3D models of plants is an important step for plant phenotyping, especially for monitoring architectural and morphological traits. Current state-of-the art approaches rely on hand-crafted 3D local features for modeling geometric variations in plant structures. While recent advancements in deep learning on point clouds have the potential of extracting relevant local and global characteristics, the scarcity of labeled 3D plant data impedes the exploration of this potential. We adapted six recent point-based deep learning architectures (PointNet, PointNet++, DGCNN, PointCNN, ShellNet, RIConv) for segmentation of structural parts of rosebush models. We generated 3D synthetic rosebush models to provide adequate amount of labeled data for modification and pre-training of these architectures. To evaluate their performance on real rosebush plants, we used the ROSE-X data set of fully annotated point cloud models. We provided experiments with and without the incorporation of synthetic data to demonstrate the potential of point-based deep learning techniques even with limited labeled data of real plants. The experimental results show that PointNet++ produces the highest segmentation accuracy among the six point-based deep learning methods. The advantage of PointNet++ is that it provides a flexibility in the scales of the hierarchical organization of the point cloud data. Pre-training with synthetic 3D models boosted the performance of all architectures, except for PointNet.