Hugging Face's logo

jingheya
/
lotus-depth-d-v2-0-disparity

Depth Estimation
Diffusers
Safetensors
DirectRegressionPipeline
Model card Files Community
jingheya commited on
Commit
ddc9f4a
•
1 Parent(s): 0bd8998

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -7,7 +7,9 @@ pipeline_tag: depth-estimation
7
  # Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
8
 
9
  <!-- Provide a quick summary of what the model is/does. -->
10
- This model belongs to the family of official Lotus models.
 
 
11
 
12
  [![Paper](https://img.shields.io/badge/Project-Website-pink?logo=googlechrome&logoColor=white)](https://lotus3d.github.io/)
13
  [![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2409.18124)
 
7
  # Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
8
 
9
  <!-- Provide a quick summary of what the model is/does. -->
10
+ - This model belongs to the family of official Lotus models.
11
+ - Compared to the [previous version](https://huggingface.co/jingheya/lotus-depth-d-v1-0), this model is trained in disparity space (inverse depth), achieving better performance and more stable video depth estimation.
12
+
13
 
14
  [![Paper](https://img.shields.io/badge/Project-Website-pink?logo=googlechrome&logoColor=white)](https://lotus3d.github.io/)
15
  [![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2409.18124)