DNN-Buddies: A Deep Neural Network-Based Estimation Metric for the Jigsaw Puzzle Problem
This work addresses the jigsaw puzzle problem for computer vision and puzzle-solving applications, representing an incremental improvement by enhancing an existing solver with a novel metric.
The paper tackles the jigsaw puzzle problem by introducing the first deep neural network-based estimation metric that predicts adjacency between puzzle pieces using only pixel data, achieving extremely high precision and significantly increasing solution accuracy to set a new state-of-the-art standard.
This paper introduces the first deep neural network-based estimation metric for the jigsaw puzzle problem. Given two puzzle piece edges, the neural network predicts whether or not they should be adjacent in the correct assembly of the puzzle, using nothing but the pixels of each piece. The proposed metric exhibits an extremely high precision even though no manual feature extraction is performed. When incorporated into an existing puzzle solver, the solution's accuracy increases significantly, achieving thereby a new state-of-the-art standard.