Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: depth-estimation
|
6 |
+
library_name: coreml
|
7 |
+
tags:
|
8 |
+
- depth
|
9 |
+
- relative depth
|
10 |
+
base_model:
|
11 |
+
- depth-anything/Depth-Anything-V2-Large
|
12 |
+
---
|
13 |
+
|
14 |
+
# Depth Anything V2 Large (mlpackage)
|
15 |
+
|
16 |
+
In this repo you can find:
|
17 |
+
* The notebook which was used to convert [depth-anything/Depth-Anything-V2-Large](https://huggingface.co/depth-anything/Depth-Anything-V2-Large) into a CoreML package.
|
18 |
+
* The mlpackage which can be opened in Xcode and used for Preview and development of macOS and iOS Apps
|
19 |
+
* Performence and compute unit mapping report for this model as meassured on an iPhone 16 Pro Max and a MacBook Pro (With Apple M3 Pro)
|
20 |
+
|
21 |
+
As a derivative work of Depth-Anything-V2-Large this port is also under cc-by-nc-4.0
|
22 |
+
|
23 |
+
|
24 |
+
## Citation of original work
|
25 |
+
|
26 |
+
If you find this project useful, please consider citing:
|
27 |
+
|
28 |
+
```bibtex
|
29 |
+
@article{depth_anything_v2,
|
30 |
+
title={Depth Anything V2},
|
31 |
+
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
|
32 |
+
journal={arXiv:2406.09414},
|
33 |
+
year={2024}
|
34 |
+
}
|
35 |
+
|
36 |
+
@inproceedings{depth_anything_v1,
|
37 |
+
title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data},
|
38 |
+
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
|
39 |
+
booktitle={CVPR},
|
40 |
+
year={2024}
|
41 |
+
}
|
42 |
+
|