DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

DiffAssemble is a unified learning-based solution using diffusion models and graphs neural networks for reassembly tasks that achieve SOTA results in most 2D and 3D without distinguishing between the two.

Data and Resources

Cite this as

Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari, Pietro Morerio, Alessio Del Bue (2024). Dataset: DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly. https://doi.org/10.57702/m60uh14y

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2402.19302
Author Gianluca Scarpellini
More Authors
Stefano Fiorini
Francesco Giuliari
Pietro Morerio
Alessio Del Bue
Homepage https://github.com/IIT-PAVIS/DiffAssemble