depth-anything

/

DA3-GIANT

like 17

Follow

Depth Aything 408

This PR enhances the model card by:

• Updating the pipeline_tag from depth-estimation to image-to-3d to more accurately reflect the model's comprehensive capabilities, including camera pose estimation and 3D Gaussian estimation. The depth-estimation tag is retained in the general tags list.
• Adding specific tags such as 3d-gaussian-splatting and 3d-reconstruction to further improve discoverability for these advanced functionalities.
• Correcting all paper links in the model card:
  • The arXiv badge now links to the official arXiv paper: https://arxiv.org/abs/2511.10647.
  • The "For detailed benchmarks" link and the "Paper" link in the "Links" section now point to the Hugging Face paper page: https://huggingface.co/papers/2511.10647.
  • The BibTeX citation's journal entry has been updated with the correct arXiv ID.

These changes ensure the model card is more informative, discoverable, and accurate.