Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| 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 |