Robust and flexible puzzle solving with corner-based cycle consistent correspondences

Wang, T., Vladimirov, K., Goh, S., Lai, Y-K., Xie, X. and Tam, G. K. L. 2019. Robust and flexible puzzle solving with corner-based cycle consistent correspondences. Presented at: EG UK Computer Graphics & Visual Computing, Bangor, UK, 12-13 September 2019. Published in: Tam, G. K. L. and Roberts, J. C. eds. EG UK Computer Graphics & Visual Computing. The Eurographics Association,

Preview

PDF - Accepted Post-Print Version Download (22MB) | Preview

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

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	The Eurographics Association
Related URLs:	Organisation
Date of First Compliant Deposit:	6 August 2019
Date of Acceptance:	22 July 2019
Last Modified:	13 Sep 2019 02:05
URI:	http://orca.cf.ac.uk/id/eprint/124757

Actions (repository staff only)

Edit Item