# Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

arXiv: https://arxiv.org/abs/2305.16963 · HTML: https://mlsanity.com/paper/2305.16963/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance](https://mlsanity.com/paper/2007.09267/) (2020)
- [GeoNet: Deep Geodesic Networks for Point Cloud Analysis](https://mlsanity.com/paper/1901.00680/) (2019)

## Built on by (most cited first, 6 of 6)

- [ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds](https://mlsanity.com/paper/2506.16991/) (2025)
- [SelvaBox: A high-resolution dataset for tropical tree crown detection](https://mlsanity.com/paper/2507.00170/) (2025)
- [SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests](https://mlsanity.com/paper/2606.08206/) (2026)
- [PointsToWood: A deep learning framework for complete canopy leaf-wood segmentation of TLS data across diverse European forests](https://mlsanity.com/paper/2503.04420/) (2025)
- [Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset](https://mlsanity.com/paper/2511.00653/) (2025)
- [CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests](https://mlsanity.com/paper/2608.30149/) (2026)

## Abstract (arXiv)

LiDAR (Light Detection and Ranging) has become an essential part of the remote sensing toolbox used for biosphere monitoring. In particular, LiDAR provides the opportunity to map forest leaf area with unprecedented accuracy, while leaf area has remained an important source of uncertainty affecting models of gas exchanges between the vegetation and the atmosphere. Unmanned Aerial Vehicles (UAV) are easy to mobilize and therefore allow frequent revisits to track the response of vegetation to climate change. However, miniature sensors embarked on UAVs usually provide point clouds of limited density, which are further affected by a strong decrease in density from top to bottom of the canopy due to progressively stronger occlusion. In such a context, discriminating leaf points from wood points presents a significant challenge due in particular to strong class imbalance and spatially irregular sampling intensity. Here we introduce a neural network model based on the Pointnet ++ architecture which makes use of point geometry only (excluding any spectral information). To cope with local data sparsity, we propose an innovative sampling scheme which strives to preserve local important geometric information. We also propose a loss function adapted to the severe class imbalance. We show that our model outperforms state-of-the-art alternatives on UAV point clouds. We discuss future possible improvements, particularly regarding much denser point clouds acquired from below the canopy.