Learning to Infer Parameterized Representations of Plants from 3D Scans
This addresses the challenge of accurately modeling plant structures for applications in botany or agriculture, but it is incremental as it builds on existing procedural models and neural networks.
The authors tackled the problem of reconstructing 3D plant architectures from scans by proposing a unified approach that infers a parameterized representation, achieving results on-par with state-of-the-art for tasks like reconstruction, segmentation, and skeletonization on Chenopodium Album plants.
Reconstructing faithfully the 3D architecture of plants from unstructured observations is a challenging task. Plants frequently contain numerous organs, organized in branching systems in more or less complex spatial networks, leading to specific computational issues due to self-occlusion or spatial proximity between organs. Existing works either consider inverse modeling where the aim is to recover the procedural rules that allow to simulate virtual plants, or focus on specific tasks such as segmentation or skeletonization. We propose a unified approach that, given a 3D scan of a plant, allows to infer a parameterized representation of the plant. This representation describes the plant's branching structure, contains parametric information for each plant organ, and can therefore be used directly in a variety of tasks. In this data-driven approach, we train a recursive neural network with virtual plants generated using an L-systems-based procedural model. After training, the network allows to infer a parametric tree-like representation based on an input 3D point cloud. Our method is applicable to any plant that can be represented as binary axial tree. We evaluate our approach on Chenopodium Album plants, using experiments on synthetic plants to show that our unified framework allows for different tasks including reconstruction, segmentation and skeletonization, while achieving results on-par with state-of-the-art for each task.