Saved in:
Bibliographic Details
Main Authors: Gilson, Andreas, Meyer, Lukas, Scholz, Oliver, Schmid, Ute
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21038
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915513467142144
author Gilson, Andreas
Meyer, Lukas
Scholz, Oliver
Schmid, Ute
author_facet Gilson, Andreas
Meyer, Lukas
Scholz, Oliver
Schmid, Ute
contents Accurate point cloud segmentation for plant organs is crucial for 3D plant phenotyping. Existing solutions are designed problem-specific with a focus on certain plant species or specified sensor-modalities for data acquisition. Furthermore, it is common to use extensive pre-processing and down-sample the plant point clouds to meet hardware or neural network input size requirements. We propose a simple, yet effective algorithm KDSS for sub-sampling of biological point clouds that is agnostic to sensor data and plant species. The main benefit of this approach is that we do not need to down-sample our input data and thus, enable segmentation of the full-resolution point cloud. Combining KD-SS with current state-of-the-art segmentation models shows satisfying results evaluated on different modalities such as photogrammetry, laser triangulation and LiDAR for various plant species. We propose KD-SS as lightweight resolution-retaining alternative to intensive pre-processing and down-sampling methods for plant organ segmentation regardless of used species and sensor modality.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21038
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities
Gilson, Andreas
Meyer, Lukas
Scholz, Oliver
Schmid, Ute
Computer Vision and Pattern Recognition
Accurate point cloud segmentation for plant organs is crucial for 3D plant phenotyping. Existing solutions are designed problem-specific with a focus on certain plant species or specified sensor-modalities for data acquisition. Furthermore, it is common to use extensive pre-processing and down-sample the plant point clouds to meet hardware or neural network input size requirements. We propose a simple, yet effective algorithm KDSS for sub-sampling of biological point clouds that is agnostic to sensor data and plant species. The main benefit of this approach is that we do not need to down-sample our input data and thus, enable segmentation of the full-resolution point cloud. Combining KD-SS with current state-of-the-art segmentation models shows satisfying results evaluated on different modalities such as photogrammetry, laser triangulation and LiDAR for various plant species. We propose KD-SS as lightweight resolution-retaining alternative to intensive pre-processing and down-sampling methods for plant organ segmentation regardless of used species and sensor modality.
title OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.21038