PoGO-Net: Pose Graph Optimization with Graph Neural Networks

Xinyi Li, Haibin Ling

Abstract

Pose Graph Optimization (PGO) is a critical component in 3D reconstruction and SLAM, traditionally solved via iterative optimization. This paper introduces PoGO-Net, a Graph Neural Network (GNN) framework that reformulates PGO as a message-passing problem. By incorporating a differentiable "edge-dropping" mechanism, PoGO-Net effectively filters outlier constraints that typically degrade performance. Experimental results demonstrate that PoGO-Net achieves state-of-the-art accuracy across diverse benchmarks while operating up to 400x faster than traditional CPU-based solvers.

Introduction

In computer vision tasks such as Structure-from-Motion (SfM), PGO reconciles noisy, pairwise relative camera poses into a globally consistent coordinate frame. Traditional solvers face significant challenges: high computational complexity (often cubic), extreme sensitivity to outlier measurements from poor feature matching, and limited generalization across different environments. PoGO-Net addresses these by leveraging the parallel processing power of GNNs and an integrated denoising strategy.

Methodology

PoGO-Net represents the optimization problem as a graph where nodes are absolute camera orientations and edges are relative rotation constraints.

Overview of the PoGO-Net pipeline, showing the transition from an initial view-graph to an optimized global pose-graph via iterative de-noise and GNN layers.

Differentiable Edge-Dropping

The core innovation is the De-noise Layer. Unlike standard GNNs that aggregate all neighbor information, PoGO-Net learns to predict the reliability of each edge. Using the Gumbel-Softmax trick, the network makes discrete "keep or drop" decisions differentiable. This allows the model to learn outlier rejection end-to-end during training based on local graph consistency.

Iterative Optimization

The network iteratively updates node features through message aggregation. It is initialized using a spanning tree starting from the most connected camera node to provide a stable starting point. Training is guided by a joint loss function that enforces both global geometric consistency and alignment with ground-truth poses.

Experimental Results

The framework was evaluated on benchmarks including 7Scenes, Cambridge, ScanNet, and Photo Tourism.

Accuracy and Robustness

PoGO-Net consistently outperformed both traditional robust solvers (e.g., IRLS) and previous learning-based methods. On the 7Scenes dataset, it reduced the average angular error to 4.93°, a significant improvement over the 6.33° achieved by prior state-of-the-art learning methods.

Comparison of median error in degrees across different noise levels (10% and 20% outliers). PoGO-Net maintains stability where standard GNN approaches degrade.

Computational Efficiency

The use of GNNs allows for massive parallelism on GPUs. In large-scale Photo Tourism datasets, PoGO-Net demonstrated speeds up to 400x faster than conventional CPU solvers and 2x faster than competing GNN-based approaches, making it suitable for real-time applications.

Conclusion

PoGO-Net represents a significant step forward in robust, real-time pose graph optimization. By integrating denoising directly into the GNN architecture, it overcomes the sensitivity to outliers that plagues traditional methods. Future work includes extending the framework to full $SE(3)$ regression (handling both rotation and translation) and integration into end-to-end SLAM systems.

Summary updated

Abstract

Accurate camera pose estimation or global camera re-localization is a core component in Structure-from-Motion (SfM) and SLAM systems. Given pair-wise relative camera poses, pose-graph optimization (PGO) involves solving for an optimized set of globally-consistent absolute camera poses. In this work, we propose a novel PGO scheme fueled by graph neural networks (GNN), namely PoGO-Net, to conduct the absolute camera pose regression leveraging multiple rotation averaging (MRA). Specifically, PoGO-Net takes a noisy view-graph as the input, where the nodes and edges are designed to encode the geometric constraints and local graph consistency. Besides, we address the outlier edge removal by exploiting an implicit edge-dropping scheme where the noisy or corrupted edges are effectively filtered out with parameterized networks. Furthermore, we introduce a joint loss function embedding MRA formulation such that the robust inference is capable of achieving real-time performances even for large-scale scenes. Our proposed network is trained end-to-end on public benchmarks, outperforming state-of-the-art approaches in extensive experiments that demonstrate the efficiency and robustness of our proposed network.
BibTeX
@inproceedings{li2021pogo,
  author = {Xinyi Li and Haibin Ling},
  title = {{PoGO-Net: Pose Graph Optimization with Graph Neural Networks}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  doi = {10.1109/iccv48922.2021.00584},
}
Figure