PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify

TL;DR

PuzzleFusion++ introduces an auto-agglomerative 3D fracture assembly method that iteratively aligns, merges, and verifies fragments using diffusion and transformer models, significantly outperforming existing techniques.

Contribution

The paper presents a novel auto-agglomerative approach for 3D fracture assembly, combining diffusion and transformer models for improved accuracy and efficiency.

Findings

Outperforms state-of-the-art methods by over 10% in part accuracy.

Achieves 50% improvement in Chamfer distance.

Demonstrates effectiveness on the Breaking Bad dataset.

Abstract

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.