评估用于作物表型分析的网格重建方法
Evaluating Mesh Reconstruction Methods for Crop Phenotyping
- Indian Institute of Technology Ropar（印度理工学院罗巴尔校区）
- Trinity College Dublin, The University of Dublin（都柏林圣三一大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究评估了7种3D网格重建流程用于作物表型分析，发现GGGS、PGSR和2DGS表现最佳，其中GGGS在五项指标上比2DGS高约27%。
AI中文摘要：
对农业作物进行表型分析对于研究其整个生命周期至关重要，因为它提供了提高产量乃至最终提高粮食生产的关键见解。对于在偏远地点种植的作物进行同样的分析，对于无法亲临现场的专家来说是一个挑战。3D重建技术通过实现作物数字化，使专家能够随时随地访问生成的3D作物模型，为这一问题提供了有前景的解决方案。在这项工作中，我们评估了用于作物表型分析的近期3D重建流程。我们聚焦于7种网格重建流程，并从定性和定量两方面衡量其输出的保真度和一致性。我们的结果表明，由GGGS、PGSR和2DGS生成的网格优于其他流程，这得益于其定量指标和视觉上令人满意的输出。GGGS流程在包含5个维度（即用户评分、Chamfer距离、LPIPS、PSNR和SSIM）的雷达图上比第二好的流程（2DGS）高出约27%。
英文摘要：
Phenotyping an agricultural crop is crucial for studying its entire life cycle, as it provides vital insights to improve yield and, ultimately, food production. Doing the same for crops grown on remote sites is a challenge for the specialists who cannot be available on-site. 3D reconstruction techniques offer a promising solution to this problem by enabling crop digitization, allowing specialists to access the resulting 3D crop models from anywhere at any time. In this work, we evaluate recent 3D reconstruction pipelines for crop phenotyping. We focus on 7 mesh reconstruction pipelines and measure the fidelity and consistency of their outputs qualitatively and quantitatively. Our results suggest that the meshes produced by the GGGS, PGSR, and 2DGS are preferable to the other pipelines, owing to their quantitative metrics and visually pleasing outputs. The GGGS pipeline is better than the second-best pipeline (2DGS) by about 27\% on the radar chart with 5 dimensions, namely, User ratings, Chamfer distance, LPIPS, PSNR, and SSIM.
