发表机构
Fraunhofer Institute for Integrated Circuits (IIS); Otto-Friedrich-Universität Bamberg; Friedrich-Alexander-Universität Erlangen-Nürnberg（弗劳恩霍夫集成电路研究所; 班贝格奥托·弗里德里希大学; 埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出无需标注的零样本三维植物器官分割流水线，结合SAM3与语义NeRF，在秋海棠测试台达92.6% mIoU，并在十种植物数据集上平均0.856 mIoU，接近监督方法水平。
AI 中文摘要
精确的三维植物器官分割是自动表型分析的基础。现有方法依赖于带标注的训练数据或特定物种的模型配置。我们提出了一种无需标注的三维植物器官分割流水线，将文本提示的SAM3分割与语义神经辐射场（NeRFs）相结合。仅需多视角RGB图像和类别名称列表，我们的零样本流水线即可生成带语义标签的三维点云，无需人工标注、逐物种微调或特定领域的预处理。多视角NeRF融合作为一种有效的隐式共识机制，将不完美的逐帧掩码提升为准确的三维标签。在受控的秋海棠（Begonia maculata）测试台上，SAM3流水线实现了92.6%的mIoU，达到了使用完美地面真值掩码建立的Oracle上限的95.9%。该流水线进一步在一个涵盖十种多样植物点云的新数据集上进行了评估，平均mIoU达到0.856，每个物种的叶片和花盆IoU分别高于0.91和0.90。这些结果表明，无需标注的三维植物器官分割现已可行，并接近监督方法的性能范围。
英文摘要
Accurate 3D plant organ segmentation is fundamental to automated phenotyping. Existing approaches rely on annotated training data or species-specific model configurations. We present an annotation-free pipeline for 3D plant organ segmentation, combining text-prompted SAM3 segmentation with semantic neural radiance fields (NeRFs). Given only multi-view RGB images and a list of class names, our zero-shot pipeline produces semantically labeled 3D point clouds without manual annotation, per-species fine-tuning, or domain-specific preprocessing. Multi-view NeRF fusion acts as effective implicit consensus mechanism that lifts imperfect per-frame masks into accurate 3D labels. On a controlled Begonia maculata testbed the SAM3 pipeline achieves 92.6% mIoU, reaching 95.9% of the oracle upper bound established with perfect ground-truth masks. The pipeline was further evaluated on a new dataset spanning ten diverse plant point clouds reaching an average 0.856 mIoU, with leaf and pot IoU above 0.91 and 0.90 for every species, respectively. These results demonstrate that annotation-free 3D plant organ segmentation is now feasible and approaching the range of supervised methods.
CommentsSubmitted to CVPPA Workshop at ECCV 2026
