# NeuRoRA: Neural Robust Rotation Averaging

arXiv: https://arxiv.org/abs/1912.04485 · HTML: https://mlsanity.com/paper/1912.04485/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2019.

## Built on by (most cited first, 30 of 32)

- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2303.14478/) (2023)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [HARA: A Hierarchical Approach for Robust Rotation Averaging](https://mlsanity.com/paper/2111.08831/) (2021)
- [Deep Permutation Equivariant Structure from Motion](https://mlsanity.com/paper/2104.06703/) (2021)
- [Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging](https://mlsanity.com/paper/2103.08292/) (2021)
- [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)
- [RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging](https://mlsanity.com/paper/2212.07211/) (2022)
- [Learning Structure-from-Motion with Graph Attention Networks](https://mlsanity.com/paper/2308.15984/) (2023)
- [ZeroGS: Training 3D Gaussian Splatting from Unposed Images](https://mlsanity.com/paper/2411.15779/) (2024)
- [Robustifying the Multi-Scale Representation of Neural Radiance Fields](https://mlsanity.com/paper/2210.04233/) (2022)
- [Rotation Synchronization via Deep Matrix Factorization](https://mlsanity.com/paper/2305.05268/) (2023)
- [Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images](https://mlsanity.com/paper/2311.04521/) (2023)
- [Enhanced Stable View Synthesis](https://mlsanity.com/paper/2303.17094/) (2023)
- [RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization](https://mlsanity.com/paper/2202.13221/) (2022)
- [PoserNet: Refining Relative Camera Poses Exploiting Object Detections](https://mlsanity.com/paper/2207.09445/) (2022)
- [Gravity-aligned Rotation Averaging with Circular Regression](https://mlsanity.com/paper/2410.12763/) (2024)
- [TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation](https://mlsanity.com/paper/2105.14065/) (2021)
- [A Taxonomy of Structure from Motion Methods](https://mlsanity.com/paper/2505.15814/) (2025)
- [A new dynamical model for solving rotation averaging problem](https://mlsanity.com/paper/2111.11723/) (2021)
- [Incremental Rotation Averaging Revisited](https://mlsanity.com/paper/2309.16924/) (2023)
- [Rotation Averaging: A Primal-Dual Method and Closed-Forms in Cycle Graphs](https://mlsanity.com/paper/2406.18564/) (2024)
- [Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images](https://mlsanity.com/paper/2411.12620/) (2024)
- [Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration](https://mlsanity.com/paper/2505.03692/) (2025)
- [Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM](https://mlsanity.com/paper/2510.22740/) (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)
- [Global Consistent Point Cloud Registration Based on Lie-algebraic Cohomology](https://mlsanity.com/paper/2208.07103/) (2022)
- [EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Images](https://mlsanity.com/paper/2310.10051/) (2023)
- [PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections](https://mlsanity.com/paper/2403.08586/) (2024)

## Abstract (arXiv)

Multiple rotation averaging is an essential task for structure from motion, mapping, and robot navigation. The task is to estimate the absolute orientations of several cameras given some of their noisy relative orientation measurements. The conventional methods for this task seek parameters of the absolute orientations that agree best with the observed noisy measurements according to a robust cost function. These robust cost functions are highly nonlinear and are designed based on certain assumptions about the noise and outlier distributions. In this work, we aim to build a neural network that learns the noise patterns from the data and predict/regress the model parameters from the noisy relative orientations. The proposed network is a combination of two networks: (1) a view-graph cleaning network, which detects outlier edges in the view-graph and rectifies noisy measurements; and (2) a fine-tuning network, which fine-tunes an initialization of absolute orientations bootstrapped from the cleaned graph, in a single step. The proposed combined network is very fast, moreover, being trained on a large number of synthetic graphs, it is more accurate than the conventional iterative optimization methods. Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.