# DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks

arXiv: https://arxiv.org/abs/2403.11370 · HTML: https://mlsanity.com/paper/2403.11370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 17 Mar 2024.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos](https://mlsanity.com/paper/2003.08429/) (2020)
- [4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving](https://mlsanity.com/paper/2009.06364/) (2020)
- [Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization](https://mlsanity.com/paper/2007.14628/) (2020)
- [OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure](https://mlsanity.com/paper/2202.09199/) (2022)
- [Hilti-Oxford Dataset: A Millimetre-Accurate Benchmark for Simultaneous Localization and Mapping](https://mlsanity.com/paper/2208.09825/) (2022)
- [Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation](https://mlsanity.com/paper/2103.07153/) (2021)
- [Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem](https://mlsanity.com/paper/2003.06752/) (2020)

## Abstract (arXiv)

The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images within the static part of the environment, we propose a graph neural network-based sparse feature matching network designed to perform robust matching under challenging conditions while excluding keypoints on moving objects. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks but augment the graph with epipolar and temporal information and vastly reduce the number of graph edges. Furthermore, we introduce a self-supervised training scheme to extract pseudo labels for image pairs in dynamic environments from exclusively unprocessed visual-inertial data. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks while still achieving similar results regarding conventional matching metrics. When integrated into a SLAM system, our network significantly improves performance, especially in highly dynamic scenes.