ForestFormer3D

Segments forest point clouds into individual trees and semantic classes in a single pass.

Field
Forestry & vegetation
Method
Deep learning
Data it takes
point-cloud
License
CC-BY-NC-4.0 — restricted use

ForestFormer3D is a transformer performing panoptic segmentation of forest point clouds, labeling which tree each point belongs to and what class it falls into within a single pass.

It is more recent than SegmentAnyTree and TreeLearn and can be run alongside them on the same data for comparison.

The license is CC-BY-NC-4.0, permitting non-commercial use only.

Upstream project →

Catalog entry last checked 2026-08-18. All models →

Run ForestFormer3D on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab