
The author proposes Dual-Context Aggregation Matting (DCAM) as a universal framework for image matting, emphasizing the importance of global and local context aggregation. DCAM outperforms existing methods in both automatic and interactive matting tasks.


coremsg

Dual-Context-Aggregation-for-Universal-Image-Matting-A-Comprehensive-Study


Dual-Context Aggregation for Universal Image Matting: A Comprehensive Study


title_rewrite


In-Context Matting enables automatic alpha estimation on target images using reference guidance, combining the benefits of automatic and auxiliary input-based matting.


in-context-matting-automatic-image-matting-with-reference-guidance


In-Context Matting: Automatic Image Matting with Reference Guidance
