Research

Paper

TESTING March 06, 2026

CHMv2: Improvements in Global Canopy Height Mapping using DINOv3

Authors

John Brandt, Seungeun Yi, Jamie Tolan, Xinyuan Li, Peter Potapov, Jessica Ertel, Justine Spore, Huy V. Vo, Michaël Ramamonjisoa, Patrick Labatut, Piotr Bojanowski, Camille Couprie

Abstract

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.

Metadata

arXiv ID: 2603.06382
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.06382v1</id>\n    <title>CHMv2: Improvements in Global Canopy Height Mapping using DINOv3</title>\n    <updated>2026-03-06T15:33:31Z</updated>\n    <link href='https://arxiv.org/abs/2603.06382v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.06382v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-06T15:33:31Z</published>\n    <arxiv:comment>Submitted to Nature Scientific Data</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>John Brandt</name>\n    </author>\n    <author>\n      <name>Seungeun Yi</name>\n    </author>\n    <author>\n      <name>Jamie Tolan</name>\n    </author>\n    <author>\n      <name>Xinyuan Li</name>\n    </author>\n    <author>\n      <name>Peter Potapov</name>\n    </author>\n    <author>\n      <name>Jessica Ertel</name>\n    </author>\n    <author>\n      <name>Justine Spore</name>\n    </author>\n    <author>\n      <name>Huy V. Vo</name>\n    </author>\n    <author>\n      <name>Michaël Ramamonjisoa</name>\n    </author>\n    <author>\n      <name>Patrick Labatut</name>\n    </author>\n    <author>\n      <name>Piotr Bojanowski</name>\n    </author>\n    <author>\n      <name>Camille Couprie</name>\n    </author>\n  </entry>"
}