Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method

This paper tackles the challenge of accurately segmenting images of Ming-style furniture, an important aspect of China's cultural heritage, to aid in its preservation and analysis. Existing vision foundation models, like the segment anything model (SAM), struggle with the complex structures of Ming furniture due to the need for manual prompts and imprecise segmentation outputs. To address these limitations, we introduce two key innovations: the material attribute prompter (MAP), which automatically generates prompts based on the furniture's material properties, and the structure refinement module (SRM), which enhances segmentation by combining high- and low-level features. Additionally, we present the MF2K dataset, which includes 2073 images annotated with pixel-level masks across eight materials and environments. Our experiments demonstrate that the proposed method significantly improves the segmentation accuracy, outperforming state-of-the-art models in terms of the mean intersection over union (mIoU). Ablation studies highlight the contributions of the MAP and SRM to both the performance and computational efficiency. This work offers a powerful automated solution for segmenting intricate furniture structures, facilitating digital preservation and in-depth analysis of Ming-style furniture.