reach-vb HF staff commited on
Commit
6176e04
1 Parent(s): 4c9eb5a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -6,6 +6,23 @@ license: apache-2.0
6
 
7
  See [the Files tab](https://huggingface.co/coreml-projects/depth-anything/tree/main) for converted models.
8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ## Download
10
 
11
  Install `huggingface-hub`
 
6
 
7
  See [the Files tab](https://huggingface.co/coreml-projects/depth-anything/tree/main) for converted models.
8
 
9
+ Depth Anything model was introduced in the paper [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://arxiv.org/abs/2401.10891) by Lihe Yang et al. and first released in [this repository](https://github.com/LiheYoung/Depth-Anything).
10
+
11
+ [Online demo](https://huggingface.co/spaces/LiheYoung/Depth-Anything) is also provided.
12
+
13
+ Disclaimer: The team releasing Depth Anything did not write a model card for this model so this model card has been written by the Hugging Face team.
14
+
15
+ ## Model description
16
+
17
+ Depth Anything leverages the [DPT](https://huggingface.co/docs/transformers/model_doc/dpt) architecture with a [DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2) backbone.
18
+
19
+ The model is trained on ~62 million images, obtaining state-of-the-art results for both relative and absolute depth estimation.
20
+
21
+ <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/depth_anything_overview.jpg"
22
+ alt="drawing" width="600"/>
23
+
24
+ <small> Depth Anything overview. Taken from the <a href="https://arxiv.org/abs/2401.10891">original paper</a>.</small>
25
+
26
  ## Download
27
 
28
  Install `huggingface-hub`