PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910837737783296 |
|---|---|
| author | Wang, Zhengqing Chen, Jiacheng Furukawa, Yasutaka |
| author_facet | Wang, Zhengqing Chen, Jiacheng Furukawa, Yasutaka |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00259 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify Wang, Zhengqing Chen, Jiacheng Furukawa, Yasutaka Computer Vision and Pattern Recognition 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. |
| title | PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00259 |