Smart Object Removal using LaMa + Segment Anything with Streamlit UI : A computer vision project combining Segment Anything (SAM) for dynamic object masking and LaMa for high-quality inpainting. Built with PyTorch, OpenCV, and Streamlit for a seamless user interface.

Python script generates colored masks from COCO-style annotations. It reads the COCO annotation files, creates masks for each annotation, colors the masks based on the annotation's category, and saves the colored masks as images. The script is designed to handle multiple categories and can be easily extended to support more categories if needed.