RoyYang0714

/

3D-MOOD

like 2

This PR significantly enhances the model card for 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection by:

• Adding the pipeline_tag: image-to-3d to the metadata, ensuring the model is discoverable under the "image-to-3d" pipeline on the Hugging Face Hub.
• Adding the license: apache-2.0 to the metadata for clarity regarding usage rights.
• Removing the non-standard library_name: 3D-MOOD from the metadata, as it does not correspond to a Hugging Face-supported library for automated code snippets. The model's framework, Vis4D, is mentioned in the content.
• Providing a detailed content section including the paper title, abstract, direct links to the Hugging Face paper page, the project page, and the GitHub repository.
• Integrating a clear "Demo" section with a code snippet and visualization directly from the GitHub README to showcase sample usage.
• Including relevant images from the GitHub repository to enrich the model card's visual appeal and information.

Please review and merge this PR.