Hugging Face's logo

JonnyYu828
/
DepthVLM-4B

Depth Estimation
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
vision-language-model
3d-vision
multimodal
Model card Files
xet
 Community
1
JonnyYu828 commited on
Commit
1b7c7cf
·
verified ·
1 Parent(s): b3b0bda

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -49,7 +49,7 @@ DepthVLM serves as **a unified foundation model for both low-level dense geometr
49
 
50
  By attaching a lightweight depth head to the LLM backbone and adopting a two-stage supervision paradigm, DepthVLM transforms a single VLM into a native dense geometry predictor, while preserving its multimodal capabilities and enhancing its spatial reasoning.
51
 
52
- ### Key Characteristics
53
 
54
  - **Native dense metric depth estimation in VLMs**: Directly predicts geometry within the VLM framework.
55
 
 
49
 
50
  By attaching a lightweight depth head to the LLM backbone and adopting a two-stage supervision paradigm, DepthVLM transforms a single VLM into a native dense geometry predictor, while preserving its multimodal capabilities and enhancing its spatial reasoning.
51
 
52
+ ## 🧠 Key Characteristics
53
 
54
  - **Native dense metric depth estimation in VLMs**: Directly predicts geometry within the VLM framework.
55