# Learning Iterative Robust Transformation Synchronization

arXiv: https://arxiv.org/abs/2111.00728 · HTML: https://mlsanity.com/paper/2111.00728/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Learning multiview 3D point cloud registration](https://mlsanity.com/paper/2001.05119/) (2020)
- [NeuRoRA: Neural Robust Rotation Averaging](https://mlsanity.com/paper/1912.04485/) (2019)
- [Learning Transformation Synchronization](https://mlsanity.com/paper/1901.09458/) (2019)
- [A Solution for Multi-Alignment by Transformation Synchronisation](https://mlsanity.com/paper/1410.8546/) (2014)
- [Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes](https://mlsanity.com/paper/1905.09634/) (2019)

## Built on by (most cited first, 14 of 14)

- [Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting](https://mlsanity.com/paper/2304.00467/) (2023)
- [Multiway Point Cloud Mosaicking with Diffusion and Global Optimization](https://mlsanity.com/paper/2404.00429/) (2024)
- [RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging](https://mlsanity.com/paper/2212.07211/) (2022)
- [PoserNet: Refining Relative Camera Poses Exploiting Object Detections](https://mlsanity.com/paper/2207.09445/) (2022)
- [FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)N Diffusion Refinement](https://mlsanity.com/paper/2512.09373/) (2025)
- [Incremental Multiview Point Cloud Registration with Two-stage Candidate Retrieval](https://mlsanity.com/paper/2407.07525/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [Incremental Multiview Point Cloud Registration](https://mlsanity.com/paper/2407.05021/) (2024)
- [Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images](https://mlsanity.com/paper/2411.12620/) (2024)
- [Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space](https://mlsanity.com/paper/2504.21467/) (2025)
- [Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration](https://mlsanity.com/paper/2505.03692/) (2025)
- [PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections](https://mlsanity.com/paper/2403.08586/) (2024)
- [Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization](https://mlsanity.com/paper/2409.09790/) (2024)
- [MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers](https://mlsanity.com/paper/2610.12624/) (2026)

## Abstract (arXiv)

Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions. Despite its usefulness, the problem remains challenging due to the influences from noisy and outlier relative motions, and the difficulty to model analytically and suppress them with high fidelity. In this work, we avoid handcrafting robust loss functions, and propose to use graph neural networks (GNNs) to learn transformation synchronization. Unlike previous works which use complicated multi-stage pipelines, we use an iterative approach where each step consists of a single weight-shared message passing layer that refines the absolute poses from the previous iteration by predicting an incremental update in the tangent space. To reduce the influence of outliers, the messages are weighted before aggregation. Our iterative approach alleviates the need for an explicit initialization step and performs well with identity initial poses. Although our approach is simple, we show that it performs favorably against existing handcrafted and learned synchronization methods through experiments on both SO(3) and SE(3) synchronization.