Browsing by Author "Tam, G. K. L."

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Robust and Flexible Puzzle Solving with Corner-based Cycle Consistent Correspondences
    (The Eurographics Association, 2019) Wang, T.; Vladimirov, K.; Goh, S.; Lai, Y.-K.; Xie, X.; Tam, G. K. L.; Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.
    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.
  • Thumbnail Image
    Item
    Shape Correspondence with Isometric and Non-Isometric Deformations
    (The Eurographics Association, 2019) Dyke, R. M.; Stride, C.; Lai, Y.-K.; Rosin, P. L.; Aubry, M.; Boyarski, A.; Bronstein, A. M.; Bronstein, M. M.; Cremers, D.; Fisher, M.; Groueix, T.; Guo, D.; Kim, V. G.; Kimmel, R.; Lähner, Z.; Li, K.; Litany, O.; Remez, T.; Rodolà, E.; Russell, B. C.; Sahillioglu, Y.; Slossberg, R.; Tam, G. K. L.; Vestner, M.; Wu, Z.; Yang, J.; Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
    The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of- the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.