ForestSplat: Proof-of-Concept for a Scalable and High-Fidelity Forestry Mapping Tool Using 3D Gaussian Splatting

Abstract

Accurate, scalable forestry insights are critical for implementing carbon credit-based reforestation initiatives and data-driven ecosystem management. However, existing forest quantification methods face significant challenges: hand measurement is labor-intensive, time-consuming, and difficult to trust; satellite imagery is not accurate enough; and airborne LiDAR remains prohibitively expensive at scale. In this work, we introduce ForestSplat: an accurate and scalable reforestation monitoring, reporting, and verification (MRV) system built from consumer-grade drone footage and 3D Gaussian Splatting. To evaluate the performance of our approach, we map and reconstruct a 200-acre mangrove restoration project in the Jobos Bay National Estuarine Research Reserve. ForestSplat produces an average mean absolute error (MAE) of 0.17 m and mean error (ME) of 0.007 m compared to canopy height maps derived from airborne LiDAR scans, using 100× cheaper hardware. We hope that our proposed framework can support the advancement of accurate and scalable forestry modeling with consumer-grade drones and computer vision, facilitating a new gold standard for reforestation MRV.

Plant phenotyping relevance

ドローン映像と3D Gaussian Splattingにより森林キャノピー高を推定する手法を開発し、航空LiDARと比較検証しているため、植物キャノピー形質の取得方法が中心である。

Code and data availability

The paper describes a paper-specific dataset (200-acre airborne LiDAR scans and 13,657 drone images) that the authors state they open-source, but no public repository URL or identifier is provided; the Data Availability Statement directs inquiries to the corresponding author or the company website. The gsplat GitHub链接是

No evidence-backed public reproduction asset is currently recorded.