huangjun12/MTADataset
收藏官方服务:
资源简介:
MTADataset是一个大规模的图像修复数据集。它为每张图像使用Grounded-SAM提取标签、边界框和掩码,然后使用LLaVA为大约5个掩码提供详细的描述,包括掩码的内容和风格信息。
MTADataset is a large-scale dataset designed for image inpainting. For each image, it uses Grounded-SAM to extract labels, bounding boxes, and masks, and LLaVA to provide detailed descriptions for approximately 5 masks per image, including information about their content and style.
提供机构:
huangjun12


