无需标注数据，3分钟内快速提取水稻小麦粒级表型点云
IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusion
- 用NeRF-SAM2融合将2D分割图升维到3D，实现多目标点云提取
- 水稻粒级mIoU达63.72%，小麦达89.68%，表型预测R2超0.97
- 单次交互即可完成多目标分割，适合高通量智能育种场景
先进植物表型技术对定向性状改良和加速智能育种至关重要。由于植物物种多样性，现有方法严重依赖大规模高精度人工标注数据。对于谷粒级自遮挡物体，无监督方法常失效。本研究提出IPENS，一种交互式无监督多目标点云提取方法。该方法利用辐射场信息，将SAM2（Segment Anything Model 2）分割的2D掩码提升至3D空间，实现目标点云提取。设计多目标协同优化策略，有效解决单次交互多目标分割难题。实验验证表明，IPENS在水稻数据集上粒级分割准确率（mIoU）达63.72%，具备强表型估计能力：谷粒体积预测R²=0.7697（RMSE=0.0025），叶面积R²=0.84（RMSE=18.93），叶长宽预测分别达到R²=0.97、0.87（RMSE=1.49、0.21）。在小麦数据集上，分割准确率进一步提升至89.68%（mIoU），表型估计表现同样优异：穗体积预测R²=0.9956（RMSE=0.0055），叶面积R²=1.00（RMSE=0.67），叶长宽预测达到R²=0.99、0.92（RMSE=0.23、0.15）。该方法为水稻与小麦提供非侵入式高质量表型提取方案，仅需单次图像交互，3分钟内完成多目标谷粒级点云提取，显著提升智能育种效率。
原文摘要 · Abstract (English)
Advanced plant phenotyping technologies play a crucial role in targeted trait improvement and accelerating intelligent breeding. Due to the species diversity of plants, existing methods heavily rely on large-scale high-precision manually annotated data. For self-occluded objects at the grain level, unsupervised methods often prove ineffective. This study proposes IPENS, an interactive unsupervised multi-target point cloud extraction method. The method utilizes radiance field information to lift 2D masks, which are segmented by SAM2 (Segment Anything Model 2), into 3D space for target point cloud extraction. A multi-target collaborative optimization strategy is designed to effectively resolve the single-interaction multi-target segmentation challenge. Experimental validation demonstrates that IPENS achieves a grain-level segmentation accuracy (mIoU) of 63.72% on a rice dataset, with strong phenotypic estimation capabilities: grain volume prediction yields R2 = 0.7697 (RMSE = 0.0025), leaf surface area R2 = 0.84 (RMSE = 18.93), and leaf length and width predictions achieve R2 = 0.97 and 0.87 (RMSE = 1.49 and 0.21). On a wheat dataset,IPENS further improves segmentation accuracy to 89.68% (mIoU), with equally outstanding phenotypic estimation performance: spike volume prediction achieves R2 = 0.9956 (RMSE = 0.0055), leaf surface area R2 = 1.00 (RMSE = 0.67), and leaf length and width predictions reach R2 = 0.99 and 0.92 (RMSE = 0.23 and 0.15). This method provides a non-invasive, high-quality phenotyping extraction solution for rice and wheat. Without requiring annotated data, it rapidly extracts grain-level point clouds within 3 minutes through simple single-round interactions on images for multiple targets, demonstrating significant potential to accelerate intelligent breeding efficiency.
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。