动态调整粒度提升跨物种植物器官分割精度
Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation
- 根据植物特性自动选择最佳空间粒度，优化几何特征提取
- 在多个数据集上平均mIoU达88.9%，比固定粒度方法高2.5点
- 仅需少量标注数据，适合资源有限的植物表型研究
近期的3D基础模型通过控制空间粒度提供了强大的点云学习特征表示。然而，依赖固定空间粒度会严重限制在植物表型等应用中的泛化能力，因为不同物种和生长阶段的器官形态与尺寸差异显著。为此，我们提出AGS-PlantSeg，一种基于冻结的Utonia（arXiv:2603.03283）基础模型并结合自适应粒度选择的少样本3D植物器官分割方法。通过为每个特定植物模型动态选择最优粒度层级，该方法为轻量级MLP分割头提取优化后的几何特征。在PLANesT-3D（arXiv:2407.21150）、Pheno4D和Crops3D上的大量实验表明，AGS-PlantSeg显著提升了跨物种泛化能力，平均mIoU达到88.9%，较固定粒度基线提升2.5 mIoU点。尽管仅需极少标注数据，其性能仍可媲美全监督、专用于植物的架构。
原文摘要 · Abstract (English)
Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。