Hugging Face's logo

depth-anything
/
DA3-SMALL

Depth Estimation
Safetensors
depth-anything-3
computer-vision
monocular-depth
multi-view-geometry
pose-estimation
Model card Files
xet
Community
1

Update pipeline tag to `image-to-3d` and correct paper links

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+7
-7
nielsr

This PR improves the model card by:

  • Updating the pipeline_tag from depth-estimation to image-to-3d. This change better reflects the model's comprehensive capabilities, including 3D reconstruction, pose estimation, and spatially consistent geometry prediction, ensuring better discoverability on the Hugging Face Hub.
  • Correcting placeholder arXiv paper links throughout the model card, including the paper badge, the "Performance" section, the BibTeX citation, and the "Links" section, to https://arxiv.org/abs/2511.10647.
 Update pipeline tag to `image-to-3d` and correct paper linksea17644f
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment