PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify
This addresses the challenge of reconstructing broken 3D objects for applications in archaeology, forensics, or digital restoration, representing a strong specific gain rather than a foundational advance.
The paper tackles the problem of 3D fracture assembly by proposing PuzzleFusion++, an auto-agglomerative method that aligns and merges fragments iteratively, achieving over 10% improvement in part accuracy and 50% in Chamfer distance on the Breaking Bad dataset compared to state-of-the-art techniques.
This paper proposes a novel "auto-agglomerative" 3D fracture assembly method, PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from individual fragments, the approach 1) aligns and merges fragments into larger groups akin to agglomerative clustering and 2) repeats the process iteratively in completing the assembly akin to auto-regressive methods. Concretely, a diffusion model denoises the 6-DoF alignment parameters of the fragments simultaneously, and a transformer model verifies and merges pairwise alignments into larger ones, whose process repeats iteratively. Extensive experiments on the Breaking Bad dataset show that PuzzleFusion++ outperforms all other state-of-the-art techniques by significant margins across all metrics, in particular by over 10% in part accuracy and 50% in Chamfer distance. The code will be available on our project page: https://puzzlefusion-plusplus.github.io.