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.

使用不同的神经辐射场（NeRFs）技术，通过评估对不同环境中的植物进行（3D）重建的方法，展示了 NeRF 在详细和真实的植物建模中的潜力，并提出了增强 3D 重建过程速度和效率的实用方法。