用点云和无人机影像预测作物生物量，精度显著提升。
NeFF-BioNet: Crop Biomass Prediction from Point Cloud to Drone Imagery
- 结合稀疏3D卷积与Transformer，处理点云数据预测生物量。
- 点云模态相对提升6.1%，图像模态提升7.9%。
- 支持低成本无人机采集，适合大田规模化应用。
作物生物量对植物健康与产量评估至关重要，但现有测量方法劳动密集、破坏性强且精度不足，难以实现大规模量化。为此，我们提出一种跨模态生物量预测网络（BioNet），可处理点云与无人机影像数据。BioNet采用稀疏3D卷积神经网络与基于Transformer的预测模块，用于点云等三维数据建模。为拓展至无人机图像，引入神经特征场（NeFF）模块，将视觉基础模型的2D语义特征映射至对应3D表面，实现结构重建。在两个公开点云数据集上，BioNet相比当前最优方法相对提升约6.1%；在RGB图像模态下，结合NeFF的方案实现7.9%相对提升。该方法使用成本低、便携的机载相机，具备大规模田间应用潜力。
原文摘要 · Abstract (English)
Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.
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。