# Image Reassembly Combining Deep Learning and Shortest Path Problem

arXiv: https://arxiv.org/abs/1809.00898 · HTML: https://mlsanity.com/paper/1809.00898/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2018.

## Built on by (most cited first, 7 of 7)

- [Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer](https://mlsanity.com/paper/2207.11971/) (2022)
- [JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks](https://mlsanity.com/paper/2101.07555/) (2021)
- [Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers](https://mlsanity.com/paper/2404.07292/) (2024)
- [ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps](https://mlsanity.com/paper/2504.09608/) (2025)
- [Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment](https://mlsanity.com/paper/2106.02845/) (2021)
- [VLHSA: Vision-Language Hierarchical Semantic Alignment for Jigsaw Puzzle Solving with Eroded Gaps](https://mlsanity.com/paper/2509.25202/) (2025)
- [Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search](https://mlsanity.com/paper/2302.00384/) (2023)

## Abstract (arXiv)

This paper addresses the problem of reassembling images from disjointed fragments. More specifically, given an unordered set of fragments, we aim at reassembling one or several possibly incomplete images. The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline.