# GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image

arXiv: https://arxiv.org/abs/2207.05634 · HTML: https://mlsanity.com/paper/2207.05634/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimization](https://mlsanity.com/paper/2005.12548/) (2020)
- [Learning Representations of Sets through Optimized Permutations](https://mlsanity.com/paper/1812.03928/) (2018)
- [Solving Jigsaw Puzzles with Eroded Boundaries](https://mlsanity.com/paper/1912.00755/) (2019)
- [A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles](https://mlsanity.com/paper/1711.06769/) (2017)
- [Complementarity-Preserving Fracture Morphology for Archaeological Fragments](https://mlsanity.com/paper/1901.05726/) (2019)

## Built on by (most cited first, 10 of 10)

- [DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly](https://mlsanity.com/paper/2402.19302/) (2024)
- [Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving](https://mlsanity.com/paper/2410.24010/) (2024)
- [Multi-Phase Relaxation Labeling for Square Jigsaw Puzzle Solving](https://mlsanity.com/paper/2303.14793/) (2023)
- [Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models](https://mlsanity.com/paper/2303.11120/) (2023)
- [PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models](https://mlsanity.com/paper/2511.06315/) (2025)
- [The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments](https://mlsanity.com/paper/2605.12077/) (2026)
- [ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction](https://mlsanity.com/paper/2505.21117/) (2025)
- [Benchmarking Content-Based Puzzle Solvers on Corrupted Jigsaw Puzzles](https://mlsanity.com/paper/2507.07828/) (2025)
- [JigSync: Gauge-Resolved Synchronization for Jigsaw Reassembly under Unknown Piece Orientation](https://mlsanity.com/paper/2609.18379/) (2026)
- [Fix the Match, Not the Solver: STITCH -- a Self-Supervised Compatibility Measure for Eroded Visual Puzzles](https://mlsanity.com/paper/2610.13176/) (2026)

## Abstract (arXiv)

Puzzle solving is a combinatorial challenge due to the difficulty of matching adjacent pieces. Instead, we infer a mental image from all pieces, which a given piece can then be matched against avoiding the combinatorial explosion. Exploiting advancements in Generative Adversarial methods, we learn how to reconstruct the image given a set of unordered pieces, allowing the model to learn a joint embedding space to match an encoding of each piece to the cropped layer of the generator. Therefore we frame the problem as a R@1 retrieval task, and then solve the linear assignment using differentiable Hungarian attention, making the process end-to-end. In doing so our model is puzzle size agnostic, in contrast to prior deep learning methods which are single size. We evaluate on two new large-scale datasets, where our model is on par with deep learning methods, while generalizing to multiple puzzle sizes.