Evaluating NeRFs for 3D Plant Geometry Reconstruction in Field Conditions

arXiv:2402.10344v1 Announce Type: new
Abstract: 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 …

abstract arxiv cs.cv environments fields geometry neural radiance fields plants struggle type understanding