PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation

Abstract

Modern crop breeding demands precise organ-level analysis for trait quantification, making plant point cloud segmentation (PPCS) increasingly important. However, conventional deep learning approaches rely heavily on densely annotated datasets that are labor-intensive to acquire. Unified PPCS adaptation from distribution-shifted examples with minimal additional training remains challenging. To address this, we propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning to explicitly align features across spatial scales and an information-restricted decoding strategy that prevents reconstruction shortcuts and promotes robust adaptation. The resulting pre-training enables stable few-shot generalization across species and sensing conditions, while unified fine-tuning with inherited thresholds further reduces adaptation overhead. Under full supervision on Soybean3D, PlantC2USeg achieves the highest semantic IoU and instance mWCov among compared methods, at 91.91% and 94.62%. With 20 labeled samples, it leads both metrics at 89.78% and 90.27%; with only 10 samples, it retains the highest mWCov of 83.23% while achieving 83.19% IoU. Across HR3D, 10-shot transfer to tobacco, tomato, and sorghum averages 78.41% IoU and 79.42% mWCov, while 22-shot transfer to SYAU-Maize achieves the highest IoU and mRec at 92.75% and 93.51%. Furthermore, a leading category-averaged mIoU of 85.0% on ShapeNet Part demonstrates the framework's capability to handle diverse shape variations beyond agricultural domains. These results demonstrate that PlantC2USeg reduces overall adaptation effort under distribution shifts, enabling scalable plant phenotyping and transferable 3D representation learning beyond agriculture.

Plant phenotyping relevance

植物点群の器官レベル形質定量を目的とするセグメンテーション手法を開発し、複数データセット・作物・ショット条件で性能評価しているため、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks contain no public code, data, or model availability statements. The paper uses Soybean3D, HR3D, SYAU-Maize, and ShapeNet Part datasets and mentions extending Soybean3D, but no authors' public URL, repository, or deposit language for any paper-specific asset appears in the provided text. All listed '

No evidence-backed public reproduction asset is currently recorded.