Saved in:
Bibliographic Details
Main Authors: Rika, Daniel, Sholomon, Dror, David, Eli, Pais, Alexandre, Netanyahu, Nathan S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.19325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929693243998208
author Rika, Daniel
Sholomon, Dror
David, Eli
Pais, Alexandre
Netanyahu, Nathan S.
author_facet Rika, Daniel
Sholomon, Dror
David, Eli
Pais, Alexandre
Netanyahu, Nathan S.
contents This paper presents a versatile hybrid framework for addressing 2D real-world reconstruction tasks formulated as jigsaw puzzle problems (JPPs) with square, non-overlapping pieces. Our approach integrates a deep learning (DL)-based compatibility measure (CM) model that evaluates pairs of puzzle pieces holistically, rather than focusing solely on their adjacent edges as traditionally done. This DL-based CM is paired with an optimized genetic algorithm (GA)-based solver, which iteratively searches for a global optimal arrangement using the pairwise CM scores of the puzzle pieces. Extensive experimental results highlight the framework's adaptability and robustness across multiple real-world domains. Notably, our unique hybrid methodology achieves state-of-the-art (SOTA) results in reconstructing Portuguese tile panels and large degraded puzzles with eroded boundaries.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19325
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Generic Hybrid Framework for 2D Visual Reconstruction
Rika, Daniel
Sholomon, Dror
David, Eli
Pais, Alexandre
Netanyahu, Nathan S.
Computer Vision and Pattern Recognition
This paper presents a versatile hybrid framework for addressing 2D real-world reconstruction tasks formulated as jigsaw puzzle problems (JPPs) with square, non-overlapping pieces. Our approach integrates a deep learning (DL)-based compatibility measure (CM) model that evaluates pairs of puzzle pieces holistically, rather than focusing solely on their adjacent edges as traditionally done. This DL-based CM is paired with an optimized genetic algorithm (GA)-based solver, which iteratively searches for a global optimal arrangement using the pairwise CM scores of the puzzle pieces. Extensive experimental results highlight the framework's adaptability and robustness across multiple real-world domains. Notably, our unique hybrid methodology achieves state-of-the-art (SOTA) results in reconstructing Portuguese tile panels and large degraded puzzles with eroded boundaries.
title A Generic Hybrid Framework for 2D Visual Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.19325