Jiakui

/

MaskDCPT

like 2

This pull request significantly enhances the model card for the MaskDCPT model by:

• Adding library_name: basicsr to the metadata, as evidence in the GitHub README (e.g., python basicsr/test.py) indicates compatibility and usage of the BasicSR library.
• Including the full abstract of the paper Universal Image Restoration Pre-training via Masked Degradation Classification.
• Providing a detailed "Model Overview" and "Results" section, embedding figures directly from the GitHub repository to visually demonstrate the model's pipeline and performance.
• Adding comprehensive information about the UIR-2.5M dataset, including its key characteristics and an illustrative image.
• Incorporating a "Quick Start / Sample Usage" section with explicit setup and inference instructions, directly copied from the GitHub README.
• Adding a BibTeX citation for proper attribution.

This update makes the model card much more informative, visually appealing, and user-friendly, providing all necessary context for researchers and practitioners.