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.
We visualize all the iterations of our auto-agglomerative assembly process. Each iteration runs the SE(3) Denoiser and the Pairwise Alignment Verifier to align and assemble fracture fragments into larger pieces.
\[ \text{X/Y} = \frac{\# \text{ of correct fragments}}{\# \text{ of all the fragments}} \]
@article{wang2024puzzlefusionpp,
author = {Wang, Zhengqing and Chen, Jiacheng and Furukawa, Yasutaka},
title = {PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify},
journal = {arXiv preprint arXiv:2406.00259},
year = {2024},
}