# Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar

arXiv: https://arxiv.org/abs/2304.07213 · HTML: https://mlsanity.com/paper/2304.07213/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 66 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [A high-resolution canopy height model of the Earth](https://mlsanity.com/paper/2204.08322/) (2022)
- [Continental-Scale Building Detection from High Resolution Satellite Imagery](https://mlsanity.com/paper/2107.12283/) (2021)
- [Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles](https://mlsanity.com/paper/2103.03975/) (2021)
- [Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum Inference](https://mlsanity.com/paper/1708.02287/) (2017)
- [High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach](https://mlsanity.com/paper/2212.10265/) (2022)
- [A Compromise Principle in Deep Monocular Depth Estimation](https://mlsanity.com/paper/1708.08267/) (2017)

## Built on by (most cited first, 30 of 60)

- [MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning](https://mlsanity.com/paper/2405.02771/) (2024)
- [SSL4EO-L: Datasets and Foundation Models for Landsat Imagery](https://mlsanity.com/paper/2306.09424/) (2023)
- [TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis](https://mlsanity.com/paper/2506.20380/) (2025)
- [OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation](https://mlsanity.com/paper/2511.13655/) (2025)
- [Cluster and Predict Latent Patches for Improved Masked Image Modeling](https://mlsanity.com/paper/2502.08769/) (2025)
- [Open-Canopy: Towards Very High Resolution Forest Monitoring](https://mlsanity.com/paper/2407.09392/) (2024)
- [OAM-TCD: A globally diverse dataset of high-resolution tree cover maps](https://mlsanity.com/paper/2407.11743/) (2024)
- [AGBD: A Global-scale Biomass Dataset](https://mlsanity.com/paper/2406.04928/) (2024)
- [Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation](https://mlsanity.com/paper/2408.04523/) (2024)
- [Sub-Meter Tree Height Mapping of California using Aerial Images and LiDAR-Informed U-Net Model](https://mlsanity.com/paper/2306.01936/) (2023)
- [Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation](https://mlsanity.com/paper/2501.19328/) (2025)
- [Lossy Neural Compression for Geospatial Analytics: A Review](https://mlsanity.com/paper/2503.01505/) (2025)
- [Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?](https://mlsanity.com/paper/2503.07890/) (2025)
- [Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas](https://mlsanity.com/paper/2411.14354/) (2024)
- [Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery](https://mlsanity.com/paper/2506.04970/) (2025)
- [High Resolution Tree Height Mapping of the Amazon Forest using Planet NICFI Images and LiDAR-Informed U-Net Model](https://mlsanity.com/paper/2501.10600/) (2025)
- [SelvaBox: A high-resolution dataset for tropical tree crown detection](https://mlsanity.com/paper/2507.00170/) (2025)
- [PRUE: A Practical Recipe for Field Boundary Segmentation at Scale](https://mlsanity.com/paper/2603.27101/) (2026)
- [DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications](https://mlsanity.com/paper/2502.17066/) (2025)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [On the Status of Foundation Models for SAR Imagery](https://mlsanity.com/paper/2509.21722/) (2025)
- [CHMv2: Improvements in Global Canopy Height Mapping using DINOv3](https://mlsanity.com/paper/2603.06382/) (2026)
- [SSL4SAR: Self-Supervised Learning for Glacier Calving Front Extraction from SAR Imagery](https://mlsanity.com/paper/2507.01747/) (2025)
- [MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data](https://mlsanity.com/paper/2508.10894/) (2025)
- [Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using Airborne LiDAR HD Reference Data across Metropolitan France](https://mlsanity.com/paper/2512.11524/) (2025)
- [ECHOSAT: Estimating Canopy Height Over Space And Time](https://mlsanity.com/paper/2602.21421/) (2026)
- [OlmoEarth v1.2: A more efficient family of OlmoEarth models](https://mlsanity.com/paper/2605.20804/) (2026)
- [Climate-sensitive Urban Planning through Optimization of Tree Placements](https://mlsanity.com/paper/2310.05691/) (2023)
- [First Mapping the Canopy Height of Primeval Forests in the Tallest Tree Area of Asia](https://mlsanity.com/paper/2404.14661/) (2024)
- [A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forests](https://mlsanity.com/paper/2410.18108/) (2024)

## Abstract (arXiv)

Vegetation structure mapping is critical for understanding the global carbon cycle and monitoring nature-based approaches to climate adaptation and mitigation. Repeated measurements of these data allow for the observation of deforestation or degradation of existing forests, natural forest regeneration, and the implementation of sustainable agricultural practices like agroforestry. Assessments of tree canopy height and crown projected area at a high spatial resolution are also important for monitoring carbon fluxes and assessing tree-based land uses, since forest structures can be highly spatially heterogeneous, especially in agroforestry systems. Very high resolution satellite imagery (less than one meter (1m) Ground Sample Distance) makes it possible to extract information at the tree level while allowing monitoring at a very large scale. This paper presents the first high-resolution canopy height map concurrently produced for multiple sub-national jurisdictions. Specifically, we produce very high resolution canopy height maps for the states of California and Sao Paulo, a significant improvement in resolution over the ten meter (10m) resolution of previous Sentinel / GEDI based worldwide maps of canopy height. The maps are generated by the extraction of features from a self-supervised model trained on Maxar imagery from 2017 to 2020, and the training of a dense prediction decoder against aerial lidar maps. We also introduce a post-processing step using a convolutional network trained on GEDI observations. We evaluate the proposed maps with set-aside validation lidar data as well as by comparing with other remotely sensed maps and field-collected data, and find our model produces an average Mean Absolute Error (MAE) of 2.8 meters and Mean Error (ME) of 0.6 meters.