Evaluating NeRFs for 3D Plant Geometry Reconstruction in Field Conditions
CoRR(2024)
摘要
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
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要