Edge2Vec: A High Quality Embedding for the Jigsaw Puzzle Problem. (arXiv:2211.07771v1 [cs.CV])

Pairwise compatibility measure (CM) is a key component in solving the jigsaw
puzzle problem (JPP) and many of its recently proposed variants. With the rapid
rise of deep neural networks (DNNs), a trade-off between performance (i.e.,
accuracy) and computational efficiency has become a very significant issue.
Whereas an end-to-end DNN-based CM model exhibits high performance, it becomes
virtually infeasible on very large puzzles, due to its highly intensive
computation. On the other hand, exploiting the concept of embeddings to
alleviate …

arxiv embedding jigsaw puzzle quality