OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities

Abstract

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.

Code and data availability

The paper describes the KD-SS sub-sampling algorithm and DGCNN-based segmentation experiments on public (PLANesT-3D, Sorghum) and semi-public (cherry, wheat) datasets, but provides no authors' public code, trained model checkpoints, or paper-specific data deposit. The public datasets are cited prior-work assets, not an

No evidence-backed public reproduction asset is currently recorded.