Update README.md
Browse files
README.md
CHANGED
@@ -15,6 +15,14 @@ The model checkpoint is compatible with the transformers library.
|
|
15 |
|
16 |
Depth Anything V2 was introduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses the same architecture as the original Depth Anything release but employs synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. This fine-tuned version for metric depth estimation was first released in [this repository](https://github.com/DepthAnything/Depth-Anything-V2).
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
## Model description
|
19 |
|
20 |
Depth Anything V2 leverages the [DPT](https://huggingface.co/docs/transformers/model_doc/dpt) architecture with a [DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2) backbone.
|
|
|
15 |
|
16 |
Depth Anything V2 was introduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses the same architecture as the original Depth Anything release but employs synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. This fine-tuned version for metric depth estimation was first released in [this repository](https://github.com/DepthAnything/Depth-Anything-V2).
|
17 |
|
18 |
+
**Six metric depth models** of three scales for indoor and outdoor scenes, respectively, were released and are available:
|
19 |
+
|
20 |
+
| Base Model | Params | Indoor (Hypersim) | Outdoor (Virtual KITTI 2) |
|
21 |
+
|:-|-:|:-:|:-:|
|
22 |
+
| Depth-Anything-V2-Small | 24.8M | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Indoor-Small-hf) | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Outdoor-Small-hf) |
|
23 |
+
| Depth-Anything-V2-Base | 97.5M | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf) | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Outdoor-Base-hf) |
|
24 |
+
| Depth-Anything-V2-Large | 335.3M | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Indoor-Large-hf) | [Model Card](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Outdoor-Large-hf) |
|
25 |
+
|
26 |
## Model description
|
27 |
|
28 |
Depth Anything V2 leverages the [DPT](https://huggingface.co/docs/transformers/model_doc/dpt) architecture with a [DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2) backbone.
|