Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,67 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Depth Any Canopy Base
|
| 6 |
+
|
| 7 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
+
|
| 9 |
+
This is the base version of Depth Any Canopy presented in Depth Any Canopy Paper. A [Small version](https://huggingface.co/DarthReca/depth-any-canopy-small) is also available.
|
| 10 |
+
|
| 11 |
+
## Model Details
|
| 12 |
+
|
| 13 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 14 |
+
|
| 15 |
+
The model is Depth-Anything-Base finetuned for canopy height estimation on a filtered set of [EarthView](https://huggingface.co/datasets/satellogic/EarthView).
|
| 16 |
+
|
| 17 |
+
- **License:** Apache 2.0
|
| 18 |
+
- **Finetuned from model:** [Depth-Anything-Base](https://huggingface.co/depth-anything/Depth-Anything-V2-Base-hf)
|
| 19 |
+
|
| 20 |
+
## Uses and Limitations
|
| 21 |
+
|
| 22 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 23 |
+
|
| 24 |
+
The model is capable of working with aerial imagery of NEON. The coverage is limited to the US. We cannot guarantee its generalizability over other areas of the globe.
|
| 25 |
+
The images cover only RGB channels; no study of hyperspectral imagery was done.
|
| 26 |
+
|
| 27 |
+
## How to Get Started with the Model
|
| 28 |
+
|
| 29 |
+
Use the code below to get started with the model.
|
| 30 |
+
|
| 31 |
+
```python
|
| 32 |
+
# Use a pipeline as a high-level helper
|
| 33 |
+
from transformers import pipeline
|
| 34 |
+
|
| 35 |
+
pipe = pipeline("depth-estimation", model="DarthReca/depth-any-canopy-base")
|
| 36 |
+
|
| 37 |
+
# Load model directly
|
| 38 |
+
from transformers import AutoModelForDepthEstimation
|
| 39 |
+
|
| 40 |
+
model = AutoModelForDepthEstimation.from_pretrained("DarthReca/depth-any-canopy-base")
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
+
## Environmental Impact
|
| 44 |
+
|
| 45 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 46 |
+
|
| 47 |
+
- **Carbon Emitted:** 0.14 kgCO2
|
| 48 |
+
|
| 49 |
+
Carbon emissions are estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute).
|
| 50 |
+
|
| 51 |
+
## Citation
|
| 52 |
+
|
| 53 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 54 |
+
|
| 55 |
+
**BibTeX:**
|
| 56 |
+
|
| 57 |
+
```
|
| 58 |
+
@misc{cambrin2024depthcanopyleveragingdepth,
|
| 59 |
+
title={Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation},
|
| 60 |
+
author={Daniele Rege Cambrin and Isaac Corley and Paolo Garza},
|
| 61 |
+
year={2024},
|
| 62 |
+
eprint={2408.04523},
|
| 63 |
+
archivePrefix={arXiv},
|
| 64 |
+
primaryClass={cs.CV},
|
| 65 |
+
url={https://arxiv.org/abs/2408.04523},
|
| 66 |
+
}
|
| 67 |
+
```
|