We evaluate different Neural Radiance Fields (NeRFs) techniques for reconstructing (3D) plants in varied environments, from indoor settings to outdoor fields. Traditional techniques often struggle to capture the complex details of plants, which is crucial for botanical and agricultural understanding. We evaluate three scenarios with increasing complexity and compare the results with the point cloud obtained using LiDAR as ground truth data. In the most realistic field scenario, the NeRF models achieve a 74.65% F1 score with 30 minutes of training on the GPU, highlighting the efficiency and accuracy of NeRFs in challenging environments. These findings not only demonstrate the potential of NeRF in detailed and realistic 3D plant modeling but also suggest practical approaches for enhancing the speed and efficiency of the 3D reconstruction process.

翻译：我们评估了不同神经辐射场（NeRFs）技术在多种环境（从室内场景到室外田间）中重建三维植物的效果。传统方法难以捕捉植物复杂细节，而这对于植物学和农业理解至关重要。我们评估了复杂度递增的三种场景，并将结果与激光雷达（LiDAR）获取的点云作为真实值（ground truth）数据进行对比。在最真实的田间场景中，NeRF模型在GPU上训练30分钟后取得了74.65%的F1分数，凸显了NeRF在挑战性环境下的高效性与准确性。这些发现不仅证明了NeRF在细节丰富且逼真的三维植物建模中的潜力，还提出了提升三维重建过程速度与效率的实用方法。