Solving Small-piece Jigsaw Puzzles by Maximizing Consensus

Figure 4 5 6 7 and 8 show qualitative reconstruction results on the challenging unknown orientation piece puzzles from MIT dataset [1]. We varied the number of pieces and the size of each piece for the experiments. When the size of the piece is small, previous algorithms [2, 3] drastically drop their reconstruction performance whereas our proposed algorithm keeps the performance. Our proposed algorithm reduces up to 75% error from the previous work [3] on the unknown orientation piece puzzles (P=14, K=1064).