Evaluating NeRFs for 3D Plant Geometry Reconstruction in Field Conditions

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 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.

Code and data availability

The paper describes a corn plant dataset (RGB images, camera poses, TLS ground truth) and an evaluation framework, but no block contains explicit public availability language, deposit, or authors' URL for the dataset, code, or models. allowed_urls is empty, so no actionable asset can be cited.

No evidence-backed public reproduction asset is currently recorded.