simon123905/test0325

Model Card for CHMv2

The Canopy Height Maps v2 (CHMv2) model is a DPT-based decoder estimating canopy height given satellite imagery, leveraging DINOv3 as the backbone. Building on our original high-resolution canopy height maps released in 2024, CHMv2 delivers substantial improvements in accuracy, detail, and global consistency.

Model Details

CHMv2 model was developed using the satellite DINOv3 ViT-L as the frozen backbone. Released with world-scale maps generated with it, they will help researchers and governments measure and understand every tree, gap, and canopy edge — enabling smarter biodiversity support and land-management decisions.

Usage With Transformers

Run inference on an image with the following code:

from PIL import Image
import torch

from transformers import CHMv2ForDepthEstimation, CHMv2ImageProcessorFast

processor = CHMv2ImageProcessorFast.from_pretrained("facebook/dinov3-vitl16-chmv2-dpt-head")
model = CHMv2ForDepthEstimation.from_pretrained("facebook/dinov3-vitl16-chmv2-dpt-head")

image = Image.open("image.tif")
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

depth = processor.post_process_depth_estimation(
    outputs, target_sizes=[(image.height, image.width)]
)[0]["predicted_depth"]

Model Description

• Developed by: Meta AI
• Model type: DPT head
• License: DINOv3 License

Model Sources

• Repository: https://github.com/facebookresearch/dinov3
• Paper: https://arxiv.org/abs/2603.06382

Direct Use

The model can be used without fine-tuning to obtain competitive results on various satellite datasets (paper link).