Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences

Abstract

Solving jigsaw puzzles is a classic problem in computer vision with various applications. Over the past decades, many useful approaches have been introduced. Most existing works use edge-wise similarity measures for assembling puzzles with square pieces of the same size, and recent work innovates to use the loop constraint to improve efficiency and accuracy. We observe that most existing techniques cannot be easily extended to puzzles with rectangular pieces of arbitrary sizes, and no existing loop constraints can be used to model such challenging scenarios. In this paper, we propose a new corner-wise matching approach, modelled using the MatchLift framework to solve square puzzles with cycle consistency. We further show one exciting example illustrating how puzzles with rectangular pieces of arbitrary sizes would be solved by our technique.