SPAFormer: Sequential 3D Part Assembly with Transformers

B Xu, S Zheng, Q Jin - arXiv preprint arXiv:2403.05874, 2024 - arxiv.org
We introduce SPAFormer, an innovative model designed to overcome the combinatorial
explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate …

Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving

T Tsesmelis, L Palmieri, M Khoroshiltseva… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper proposes the RePAIR dataset that represents a challenging benchmark to test
modern computational and data driven methods for puzzle-solving and reassembly tasks …

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

Z Wang, J Chen, Y Furukawa - arXiv preprint arXiv:2406.00259, 2024 - arxiv.org
This paper proposes a novel" auto-agglomerative" 3D fracture assembly method,
PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from …

" Don't forget to put the milk back!" Dataset for Enabling Embodied Agents to Detect Anomalous Situations

JF Mullen Jr, P Goyal, R Piramuthu, M Johnston… - arXiv preprint arXiv …, 2024 - arxiv.org
Home robots intend to make their users lives easier. Our work assists in this goal by
enabling robots to inform their users of dangerous or unsanitary anomalies in their home …

A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts

J Lu, Y Liang, H Han, J Hua, J Jiang, X Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Reconstructing a complete object from its parts is a fundamental problem in many scientific
domains. The purpose of this article is to provide a systematic survey on this topic. The …

3D Shape Completion with Test-Time Training

M Schopf-Kuester, Z Lähner, M Moeller - arXiv preprint arXiv:2410.18668, 2024 - arxiv.org
This work addresses the problem of\textit {shape completion}, ie, the task of restoring
incomplete shapes by predicting their missing parts. While previous works have often …

PairingNet: A Learning-Based Pair-Searching and-Matching Network for Image Fragments

R Zhou, D Xia, Y Zhang, H Pang, X Yang… - European Conference on …, 2024 - Springer
In this paper, we propose a learning-based image fragment pair-searching and-matching
approach to solve the challenging restoration problem. Existing works use rule-based …

[PDF][PDF] A New Matching Algorithm for Stone Tool Reassembly Based on Contour Points of Flake Surface

A Altansukh, M You, E Altantsetseg… - The Journal of the …, 2024 - researchgate.net
Reassembling fragmented stone tools from the Paleolithic era remains a significant
archaeological challenge. Our study addresses this challenge by introducing a matching …

Fracture Assembly with Segmentation And Iterative Registration

J Kim, I Lee, K Joo - ICASSP 2024-2024 IEEE International …, 2024 - ieeexplore.ieee.org
Reassembling broken fractures back to their original shape remains a complex challenge.
While prior research has demonstrated impressive results in domain-specific assembly …

DeepFracture: A Generative Approach for Predicting Brittle Fractures

Y Huang, T Kanai - arXiv preprint arXiv:2310.13344, 2023 - arxiv.org
In the realm of brittle fracture animation, generating realistic destruction animations with
physics simulation techniques can be computationally expensive. Although methods using …