Saved in:
Bibliographic Details
Main Authors: Brandt, John, Yi, Seungeun, Tolan, Jamie, Li, Xinyuan, Potapov, Peter, Ertel, Jessica, Spore, Justine, Vo, Huy V., Ramamonjisoa, Michaël, Labatut, Patrick, Bojanowski, Piotr, Couprie, Camille
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.06382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911493301207040
author Brandt, John
Yi, Seungeun
Tolan, Jamie
Li, Xinyuan
Potapov, Peter
Ertel, Jessica
Spore, Justine
Vo, Huy V.
Ramamonjisoa, Michaël
Labatut, Patrick
Bojanowski, Piotr
Couprie, Camille
author_facet Brandt, John
Yi, Seungeun
Tolan, Jamie
Li, Xinyuan
Potapov, Peter
Ertel, Jessica
Spore, Justine
Vo, Huy V.
Ramamonjisoa, Michaël
Labatut, Patrick
Bojanowski, Piotr
Couprie, Camille
contents Accurate canopy height information is essential for quantifying forest carbon, monitoring restoration and degradation, and assessing habitat structure, yet high-fidelity measurements from airborne laser scanning (ALS) remain unevenly available globally. Here we present CHMv2, a global, meter-resolution canopy height map derived from high-resolution optical satellite imagery using a depth-estimation model built on DINOv3 and trained against ALS canopy height models. Compared to existing products, CHMv2 substantially improves accuracy, reduces bias in tall forests, and better preserves fine-scale structure such as canopy edges and gaps. These gains are enabled by a large expansion of geographically diverse training data, automated data curation and registration, and a loss formulation and data sampling strategy tailored to canopy height distributions. We validate CHMv2 against independent ALS test sets and against tens of millions of GEDI and ICESat-2 observations, demonstrating consistent performance across major forest biomes.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06382
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CHMv2: Improvements in Global Canopy Height Mapping using DINOv3
Brandt, John
Yi, Seungeun
Tolan, Jamie
Li, Xinyuan
Potapov, Peter
Ertel, Jessica
Spore, Justine
Vo, Huy V.
Ramamonjisoa, Michaël
Labatut, Patrick
Bojanowski, Piotr
Couprie, Camille
Computer Vision and Pattern Recognition
Accurate canopy height information is essential for quantifying forest carbon, monitoring restoration and degradation, and assessing habitat structure, yet high-fidelity measurements from airborne laser scanning (ALS) remain unevenly available globally. Here we present CHMv2, a global, meter-resolution canopy height map derived from high-resolution optical satellite imagery using a depth-estimation model built on DINOv3 and trained against ALS canopy height models. Compared to existing products, CHMv2 substantially improves accuracy, reduces bias in tall forests, and better preserves fine-scale structure such as canopy edges and gaps. These gains are enabled by a large expansion of geographically diverse training data, automated data curation and registration, and a loss formulation and data sampling strategy tailored to canopy height distributions. We validate CHMv2 against independent ALS test sets and against tens of millions of GEDI and ICESat-2 observations, demonstrating consistent performance across major forest biomes.
title CHMv2: Improvements in Global Canopy Height Mapping using DINOv3
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.06382