# ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction

arXiv: https://arxiv.org/abs/2505.21117 · HTML: https://mlsanity.com/paper/2505.21117/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation](https://mlsanity.com/paper/2402.03358/) (2024)
- [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)
- [PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving](https://mlsanity.com/paper/2211.13785/) (2022)
- [Solving Archaeological Puzzles](https://mlsanity.com/paper/1812.10553/) (2018)
- [Pictorial and apictorial polygonal jigsaw puzzles from arbitrary number of crossing cuts](https://mlsanity.com/paper/2008.07644/) (2020)
- [GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image](https://mlsanity.com/paper/2207.05634/) (2022)
- [JigsawNet: Shredded Image Reassembly using Convolutional Neural Network and Loop-based Composition](https://mlsanity.com/paper/1809.04137/) (2018)
- [A Generalized Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles of Complex Types](https://mlsanity.com/paper/1711.06768/) (2017)
- [DNN-Buddies: A Deep Neural Network-Based Estimation Metric for the Jigsaw Puzzle Problem](https://mlsanity.com/paper/1711.08762/) (2017)
- [Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models](https://mlsanity.com/paper/2303.11120/) (2023)
- [PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments](https://mlsanity.com/paper/2312.08704/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments](https://mlsanity.com/paper/2605.12077/) (2026)
- [E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework](https://mlsanity.com/paper/2511.21422/) (2025)

## Abstract (arXiv)

The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original structure. In this work, we address key limitations in state-of-the-art Deep Learning methods for reassembly, namely i) scalability; ii) multimodality; and iii) real-world applicability: beyond square or simple geometric shapes, realistic and complex erosion, or other real-world problems. We propose ReassembleNet, a method that reduces complexity by representing each input piece as a set of contour keypoints and learning to select the most informative ones by Graph Neural Networks pooling inspired techniques. ReassembleNet effectively lowers computational complexity while enabling the integration of features from multiple modalities, including both geometric and texture data. Further enhanced through pretraining on a semi-synthetic dataset. We then apply diffusion-based pose estimation to recover the original structure. We improve on prior methods by 57% and 87% for RMSE Rotation and Translation, respectively.