TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps
This addresses the need for efficient 3D tree modeling in digital maps, though it is incremental as it builds on neural-based reconstruction techniques.
The paper tackles the problem of reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and DSM, and achieves better reconstruction quality and coverage compared to existing methods with strong generalization to real-world data.
We present TreeON, a novel neural-based framework for reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new training supervision strategy that combines both geometric supervision and differentiable shadow and silhouette losses to learn point cloud representations of trees without requiring species labels, procedural rules, terrestrial reconstruction data, or ground laser scans. To address the lack of ground truth data, we generate a synthetic dataset of point clouds from procedurally modeled trees and train our network on it. Quantitative and qualitative experiments demonstrate better reconstruction quality and coverage compared to existing methods, as well as strong generalization to real-world data, producing visually appealing and structurally plausible tree point cloud representations suitable for integration into interactive digital 3D maps. The codebase, synthetic dataset, and pretrained model are publicly available at https://angelikigram.github.io/treeON/.