GANzzle++: Generative approaches for jigsaw puzzle solving as local to global assignment in latent spatial representations

IF 3.9 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pattern Recognition Letters Pub Date : 2024-11-19 DOI:10.1016/j.patrec.2024.11.010
Davide Talon , Alessio Del Bue , Stuart James
{"title":"GANzzle++: Generative approaches for jigsaw puzzle solving as local to global assignment in latent spatial representations","authors":"Davide Talon ,&nbsp;Alessio Del Bue ,&nbsp;Stuart James","doi":"10.1016/j.patrec.2024.11.010","DOIUrl":null,"url":null,"abstract":"<div><div>Jigsaw puzzles are a popular and enjoyable pastime that humans can easily solve, even with many pieces. However, solving a jigsaw is a combinatorial problem, and the space of possible solutions is exponential in the number of pieces, intractable for pairwise solutions. In contrast to the classical pairwise local matching of pieces based on edge heuristics, we estimate an approximate solution image, i.e., a <em>mental image</em>, of the puzzle and exploit it to guide the placement of pieces as a piece-to-global assignment problem. Therefore, from unordered pieces, we consider conditioned generation approaches, including Generative Adversarial Networks (GAN) models, Slot Attention (SA) and Vision Transformers (ViT), to recover the solution image. Given the generated solution representation, we cast the jigsaw solving as a 1-to-1 assignment matching problem using Hungarian attention, which places pieces in corresponding positions in the global solution estimate. Results show that the newly proposed GANzzle-SA and GANzzle-VIT benefit from the early fusion strategy where pieces are jointly compressed and gathered for global structure recovery. A single deep learning model generalizes to puzzles of different sizes and improves the performances by a large margin. Evaluated on PuzzleCelebA and PuzzleWikiArts, our approaches bridge the gap of deep learning strategies with respect to optimization-based classic puzzle solvers.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"187 ","pages":"Pages 35-41"},"PeriodicalIF":3.9000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition Letters","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167865524003179","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Jigsaw puzzles are a popular and enjoyable pastime that humans can easily solve, even with many pieces. However, solving a jigsaw is a combinatorial problem, and the space of possible solutions is exponential in the number of pieces, intractable for pairwise solutions. In contrast to the classical pairwise local matching of pieces based on edge heuristics, we estimate an approximate solution image, i.e., a mental image, of the puzzle and exploit it to guide the placement of pieces as a piece-to-global assignment problem. Therefore, from unordered pieces, we consider conditioned generation approaches, including Generative Adversarial Networks (GAN) models, Slot Attention (SA) and Vision Transformers (ViT), to recover the solution image. Given the generated solution representation, we cast the jigsaw solving as a 1-to-1 assignment matching problem using Hungarian attention, which places pieces in corresponding positions in the global solution estimate. Results show that the newly proposed GANzzle-SA and GANzzle-VIT benefit from the early fusion strategy where pieces are jointly compressed and gathered for global structure recovery. A single deep learning model generalizes to puzzles of different sizes and improves the performances by a large margin. Evaluated on PuzzleCelebA and PuzzleWikiArts, our approaches bridge the gap of deep learning strategies with respect to optimization-based classic puzzle solvers.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
GANzzle++:潜在空间表征中从局部到全局分配的拼图游戏生成方法
拼图是一种流行且令人愉快的消遣方式,即使拼图块数很多,人类也能轻松解决。然而,拼图的解法是一个组合问题,可能的解法空间与拼图块的数量成指数关系,对于成对解法来说是难以解决的。与传统的基于边缘启发式的成对局部匹配相比,我们估算出了拼图的近似解图像,即心理图像,并利用它来指导拼图的摆放,将其作为一个 "拼图到整体 "的分配问题。因此,我们考虑采用条件生成法,包括生成对抗网络(GAN)模型、片段注意力(SA)和视觉转换器(ViT),来恢复无序拼图的解图像。鉴于生成的解决方案表示,我们使用匈牙利注意力将拼图解法作为 1 对 1 的分配匹配问题,将拼图块放置在全局解决方案估计中的相应位置。结果表明,新提出的 GANzzle-SA 和 GANzzle-VIT 从早期融合策略中获益匪浅,在早期融合策略中,碎片被联合压缩并收集起来,以恢复全局结构。单一深度学习模型适用于不同大小的谜题,并大大提高了性能。通过在 PuzzleCelebA 和 PuzzleWikiArts 上进行评估,我们的方法弥补了深度学习策略与基于优化的经典谜题求解器之间的差距。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Pattern Recognition Letters
Pattern Recognition Letters 工程技术-计算机:人工智能
CiteScore
12.40
自引率
5.90%
发文量
287
审稿时长
9.1 months
期刊介绍: Pattern Recognition Letters aims at rapid publication of concise articles of a broad interest in pattern recognition. Subject areas include all the current fields of interest represented by the Technical Committees of the International Association of Pattern Recognition, and other developing themes involving learning and recognition.
期刊最新文献
Geometric insights into focal loss: Reducing curvature for enhanced model calibration An explainable super-resolution visual method for micro-crack image detection Editorial Board Cellular spatial-semantic embedding for multi-label classification of cell clusters in thyroid fine needle aspiration biopsy whole slide images Improving generative trajectory prediction via collision-free modeling and goal scene reconstruction
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1