Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
This addresses a scalable framework for assembling fractured objects in archaeology and 3D vision, though it appears incremental as it builds on prior work by removing semantic reliance.
The paper tackles the problem of geometric fracture assembly without semantic information by proposing a co-creation space with multiple assemblers and a geometric-based collision loss, achieving better performance on PartNet and Breaking Bad datasets compared to state-of-the-art methods.
Geometric fracture assembly presents a challenging practical task in archaeology and 3D computer vision. Previous methods have focused solely on assembling fragments based on semantic information, which has limited the quantity of objects that can be effectively assembled. Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information. To improve the effectiveness of assembling geometric fractures without semantic information, we propose a co-creation space comprising several assemblers capable of gradually and unambiguously assembling fractures. Additionally, we introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process and enhance the results. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks. Extensive experiments and quantitative comparisons demonstrate the effectiveness of our proposed framework, which features linear computational complexity, enhanced abstraction, and improved generalization. Our code is publicly available at https://github.com/Ruiyuan-Zhang/CCS.