# Learning Transformation Synchronization

arXiv: https://arxiv.org/abs/1901.09458 · HTML: https://mlsanity.com/paper/1901.09458/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2019.

## Built on by (most cited first, 29 of 29)

- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [NeAF: Learning Neural Angle Fields for Point Normal Estimation](https://mlsanity.com/paper/2211.16869/) (2022)
- [Quantum Permutation Synchronization](https://mlsanity.com/paper/2101.07755/) (2021)
- [Scene Synthesis via Uncertainty-Driven Attribute Synchronization](https://mlsanity.com/paper/2108.13499/) (2021)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [HARA: A Hierarchical Approach for Robust Rotation Averaging](https://mlsanity.com/paper/2111.08831/) (2021)
- [Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting](https://mlsanity.com/paper/2304.00467/) (2023)
- [Learning Iterative Robust Transformation Synchronization](https://mlsanity.com/paper/2111.00728/) (2021)
- [Multiway Point Cloud Mosaicking with Diffusion and Global Optimization](https://mlsanity.com/paper/2404.00429/) (2024)
- [GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models](https://mlsanity.com/paper/2304.10523/) (2023)
- [RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging](https://mlsanity.com/paper/2212.07211/) (2022)
- [Chordal Averaging on Flag Manifolds and Its Applications](https://mlsanity.com/paper/2303.13501/) (2023)
- [A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts](https://mlsanity.com/paper/2410.14770/) (2024)
- [Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization](https://mlsanity.com/paper/2203.12633/) (2022)
- [Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation](https://mlsanity.com/paper/2110.00053/) (2021)
- [Self-Supervised Correspondence Estimation via Multiview Registration](https://mlsanity.com/paper/2212.03236/) (2022)
- [Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization](https://mlsanity.com/paper/2407.04260/) (2024)
- [SyNDock: N Rigid Protein Docking via Learnable Group Synchronization](https://mlsanity.com/paper/2305.15156/) (2023)
- [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)
- [Riemannian Functional Map Synchronization for Probabilistic Partial Correspondence in Shape Networks](https://mlsanity.com/paper/2111.14762/) (2021)
- [Non-Negative Spherical Relaxations for Universe-Free Multi-Matching and Clustering](https://mlsanity.com/paper/2310.13311/) (2023)
- [Incremental Multiview Point Cloud Registration](https://mlsanity.com/paper/2407.05021/) (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)
- [Shortest Paths in Graphs with Matrix-Valued Edges: Concepts, Algorithm and Application to 3D Multi-Shape Analysis](https://mlsanity.com/paper/2112.04165/) (2021)
- [Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization](https://mlsanity.com/paper/2409.09790/) (2024)
- [Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes](https://mlsanity.com/paper/2609.12417/) (2026)

## Abstract (arXiv)

Reconstructing the 3D model of a physical object typically requires us to align the depth scans obtained from different camera poses into the same coordinate system. Solutions to this global alignment problem usually proceed in two steps. The first step estimates relative transformations between pairs of scans using an off-the-shelf technique. Due to limited information presented between pairs of scans, the resulting relative transformations are generally noisy. The second step then jointly optimizes the relative transformations among all input depth scans. A natural constraint used in this step is the cycle-consistency constraint, which allows us to prune incorrect relative transformations by detecting inconsistent cycles. The performance of such approaches, however, heavily relies on the quality of the input relative transformations. Instead of merely using the relative transformations as the input to perform transformation synchronization, we propose to use a neural network to learn the weights associated with each relative transformation. Our approach alternates between transformation synchronization using weighted relative transformations and predicting new weights of the input relative transformations using a neural network. We demonstrate the usefulness of this approach across a wide range of datasets.