A Generic Hybrid Framework for 2D Visual Reconstruction
This work addresses reconstruction challenges in domains like cultural heritage and degraded imagery, but it is incremental as it builds on existing hybrid methods.
The paper tackles 2D visual reconstruction as jigsaw puzzle problems by integrating a deep learning-based compatibility measure with a genetic algorithm solver, achieving state-of-the-art results in reconstructing Portuguese tile panels and large degraded puzzles.
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.