Object-Centric 3D Gaussian Splatting for Traditional Carving Reconstruction
Bibliographic Data
| ID | 23312311 |
|---|---|
| Authors | J J Liu (0000-0002-2992-2389, Fuzhou University), Jiahao Liu (0000-0002-1843-0610, The Academy of Digital China (Fujian), Fuzhou University, Fuzhou 350108, China), Liyu Tang (Fuzhou University, corresponding author), Maozhang Ye (Liming Vocational University), Dayu Yu (0000-0003-1720-8302, Nanjing Normal University), Wenhao Zeng (Fuzhou University), Han Hong (0000-0002-6959-2409, Fuzhou University) |
| Year | 2026 |
| Volume | 9 |
| Issue | 7 |
| Pages | 287 |
| Publication date | 2026-07-21 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Heritage (JOURNAL) |
| Journal identifiers | ISSN: 2571-9408 • E-ISSN: 2571-9408 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/heritage9070287 |
| OpenAlex | W7169875289 |
| Language | EN |
| References cited | 34 |
Traditional carvings, such as stone and wooden carvings, are important material carriers of intangible cultural heritage craftsmanship. High-quality three-dimensional (3D) digital replicas of these carvings provide essential support for their preservation, inheritance, interpretation, and dissemination. Owing to their intricate geometries, fine surface details, diverse materials, and complex acquisition backgrounds, high-fidelity 3D reconstruction of traditional carvings remains a challenging issue. In this study, we propose an object-centric 3D Gaussian Splatting (3DGS) framework for traditional craft carving reconstruction. Built upon the baseline 3DGS model, the proposed framework leverages the advanced segmentation capability of Segment Anything Model 2 (SAM-2) to extract foreground masks and generate alpha-channel inputs, enabling the reconstruction process to focus on the target carving. In addition, depth priors are used to guide local densification in regions with insufficient Gaussian coverage, providing auxiliary support for weakly textured or locally blurred carving details. Experiments were conducted on a self-built image dataset of stone and wooden carvings collected from Hui’an County, Quanzhou, Fujian Province, China. The experimental results show that the proposed object-centric strategy effectively preserves the original visual textures and local geometric features of traditional carvings while improving rendering efficiency. Furthermore, the optimized 3D Gaussian models are exported as lightweight digital assets and integrated into Unreal Engine 5, enabling multi-perspective visualization and interactive virtual exhibition in a contextualized digital environment. These results suggest that the proposed workflow is more suitable for producing compact object-level Gaussian assets for carving exhibition, while the depth-guided module mainly improves local details in weakly textured or shallow-relief regions.
3D reconstruction · Carving · Focus (optics) · Gaussian · Process (computing) · Rendering (computer graphics) · Segmentation · Visual hull · Visualization · Workflow · Aesthetic Perception and Analysis · Generative Adversarial Networks and Image Synthesis · Image Processing and 3D Reconstruction
| Highly cited | No |
|---|