Submitted by Rachel Gardner on Tue, 21/07/2026 - 11:27
A drone swoops low over an alpine forest. It climbs suddenly to follow the contours of the sharply rising landscape. Pulses from its lidar (light detection and ranging) instrument – a laser mapping tool – rapidly scan the trees below.
The forest, however, isn’t real. The entire landscape is a synthetic rendering by a PhD student here, Yihang She, to teach algorithms how to see trees.
The ability to recognise an individual tree in the forest canopy is essential for calculating how forests grow, how they respond to climate change, and how much carbon they store. Until now, researchers developing forest vision systems would painstakingly trace the outlines of thousands of trees to provide the system with sufficient training data, a process that can take weeks.
Now, this new forest vision training simulator overcomes that bottleneck. It is the brainchild of Yihang She, who developed the technique as part of his PhD research with his co-supervisors, Professors Srinivasan Keshav, and Andrew Blake.
"In forest surveying," says Yihang, "data collection itself isn't the hard part, the hard part is cleaning and labelling that data. Without accurate individual-tree segmentation none of the downstream work is possible. That's where this study fits into the bigger picture."
The study in question, 'Scaling Up Forest Vision with Synthetic Data', has just been published in the International Journal of Computer Vision. Published alongside it is an open-source toolkit for forest modelling, CAMP3D.
Seeing the trees for the wood
Whirring, lidar-equipped quadcopters have revolutionised fieldwork. They’ve made hard-to-reach places easier to access and allowed pinpoint aerial surveys of vast areas. But computers struggle to resolve individual trees in survey data. A computer vision technique called segmentation allows computers to recognise the trees, but it requires a large amount of pre-labelled data.
In the new approach, however, the trees are already segmented because they are created by a video game engine. The researchers used Unreal Engine's procedural generation tools to build the forest. Then, they flew a simulated drone equipped with a simulated laser scanner to produce a virtual 3D point cloud just as it would have in the real world. Because the computer already knows which points belong to which tree, the resulting point cloud comes out fully labelled.
When applying the simulator-trained model to real lidar maps, the researchers still label a small number of trees for fine tuning, but only a fraction – just 2-3% – of what traditional methods require. In a comparison detailed in the study, the simulator-trained-model performed just as well as a model trained on a fully labelled real world dataset.
Learning to fly from self-driving cars
She's technique has its origins in self-driving cars. While trying to source real-world data for 3D forest reconstructions, he noticed that autonomous car manufacturers were using video game technology to manufacture endless possible scenarios for their algorithms, such as reckless driving or unexpected events. The same principle could be used to generate forest environments.
"My supervisor showed me some vegetation examples from CARLA [a self-driving-car simulator also built on the Unreal Engine] and the thought was: maybe we could generate some data from this," he says.
The researchers added a physics-based, laser simulator for forest surveys called HELIOS++, which plays the part of the drone's lidar and bundled it together to create their opensource toolkit. Cambridge Arboreal Modelling Panoptic 3D (CAMP3D) is freely available on the projects GitHub page.
Co-author Andrew Blake, Professor Emeritus of Machine Intelligence at the University of Cambridge, says the work will significantly benefit forest ecology research. Blake was a pioneer of early computer vision research behind Microsoft’s Kinect and co-developed a foreground-background segmentation method that's still found in tools like Word and Powerpoint.
"Yihang has done a beautiful piece of work here in vision simulation," he says. "It's a wonderful modern tool for AI-driven research in forest ecology and it should be widely reusable."
After succeeding with simulated laser mapping, the team have moved on to something more ambitious. By replacing the lidar with a complex simulation of scattering electromagnetic waves, the team were able to render forests as they would look to a passing satellite. According to She, this means they can now begin to probe the 'black box' inside geospatial AI models such as Cambridge University's Tessera, a foundation model for satellite data.
"It opens up the possibility of designing controlled simulations to probe what geo-foundation models have learned about physical concepts," he says.
- The forest vision research was funded by the UKRI Centre for Doctoral Training in Application of Artificial Intelligence to the study of Environmental Risks (AI4ER) and the Cambridge Centre for Carbon Credits (4C).
