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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/96 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548900437065728 |
|---|---|
| author | Yingtong Wan Wanru Wang Meng Zhang Wei Peng He Tang |
| author_facet | Yingtong Wan Wanru Wang Meng Zhang Wei Peng He Tang |
| author_sort | Yingtong Wan |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-1bfe9df8d2d94a1db9bb4abe0e8d3014 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-1bfe9df8d2d94a1db9bb4abe0e8d30142025-01-10T13:20:52ZengMDPI AGSensors1424-82202024-12-012519610.3390/s25010096Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and MethodYingtong Wan0Wanru Wang1Meng Zhang2Wei Peng3He Tang4School of Industrial Design, Hubei University of Technology, Wuhan 430068, ChinaSchool of Industrial Design, Hubei University of Technology, Wuhan 430068, ChinaSchool of Industrial Design, Hubei University of Technology, Wuhan 430068, ChinaSchool of Industrial Design, Hubei University of Technology, Wuhan 430068, ChinaSchool of Software Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaThis 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.https://www.mdpi.com/1424-8220/25/1/96cultural heritage preservationimage segmentationvision foundation modelprompt learning |
| spellingShingle | Yingtong Wan Wanru Wang Meng Zhang Wei Peng He Tang Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method Sensors cultural heritage preservation image segmentation vision foundation model prompt learning |
| title | Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method |
| title_full | Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method |
| title_fullStr | Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method |
| title_full_unstemmed | Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method |
| title_short | Advancing a Vision Foundation Model for Ming-Style Furniture Image Segmentation: A New Dataset and Method |
| title_sort | advancing a vision foundation model for ming style furniture image segmentation a new dataset and method |
| topic | cultural heritage preservation image segmentation vision foundation model prompt learning |
| url | https://www.mdpi.com/1424-8220/25/1/96 |
| work_keys_str_mv | AT yingtongwan advancingavisionfoundationmodelformingstylefurnitureimagesegmentationanewdatasetandmethod AT wanruwang advancingavisionfoundationmodelformingstylefurnitureimagesegmentationanewdatasetandmethod AT mengzhang advancingavisionfoundationmodelformingstylefurnitureimagesegmentationanewdatasetandmethod AT weipeng advancingavisionfoundationmodelformingstylefurnitureimagesegmentationanewdatasetandmethod AT hetang advancingavisionfoundationmodelformingstylefurnitureimagesegmentationanewdatasetandmethod |