# DeepTree: Modeling Trees with Situated Latents

arXiv: https://arxiv.org/abs/2305.05153 · HTML: https://mlsanity.com/paper/2305.05153/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 60 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 4 of 4)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Procedural Urban Forestry](https://mlsanity.com/paper/2008.05567/) (2020)

## Built on by (most cited first, 9 of 9)

- [GlobalMapper: Arbitrary-Shaped Urban Layout Generation](https://mlsanity.com/paper/2307.09693/) (2023)
- [Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors](https://mlsanity.com/paper/2407.10330/) (2024)
- [AWOL: Analysis WithOut synthesis using Language](https://mlsanity.com/paper/2404.03042/) (2024)
- [DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation](https://mlsanity.com/paper/2412.15200/) (2024)
- [Demeter: A Parametric Model of Crop Plant Morphology from the Real World](https://mlsanity.com/paper/2510.16377/) (2025)
- [TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation](https://mlsanity.com/paper/2411.16132/) (2024)
- [TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects](https://mlsanity.com/paper/2607.13456/) (2026)
- [Shortest-Path Decomposition for Foliage-Robust 3D Tree Modeling and Above-Ground Biomass Estimation from Point Clouds](https://mlsanity.com/paper/2506.15577/) (2025)
- [Growing a Stand, Not a Tree: Joint Canopy Generation Reproduces Crown Shyness](https://mlsanity.com/paper/2608.28692/) (2026)

## Abstract (arXiv)

In this paper, we propose DeepTree, a novel method for modeling trees based on learning developmental rules for branching structures instead of manually defining them. We call our deep neural model situated latent because its behavior is determined by the intrinsic state -- encoded as a latent space of a deep neural model -- and by the extrinsic (environmental) data that is situated as the location in the 3D space and on the tree structure. We use a neural network pipeline to train a situated latent space that allows us to locally predict branch growth only based on a single node in the branch graph of a tree model. We use this representation to progressively develop new branch nodes, thereby mimicking the growth process of trees. Starting from a root node, a tree is generated by iteratively querying the neural network on the newly added nodes resulting in the branching structure of the whole tree. Our method enables generating a wide variety of tree shapes without the need to define intricate parameters that control their growth and behavior. Furthermore, we show that the situated latents can also be used to encode the environmental response of tree models, e.g., when trees grow next to obstacles. We validate the effectiveness of our method by measuring the similarity of our tree models and by procedurally generated ones based on a number of established metrics for tree form.