# AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation

arXiv: https://arxiv.org/abs/2206.12946 · HTML: https://mlsanity.com/paper/2206.12946/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 26 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Language Modeling with Deep Transformers](https://mlsanity.com/paper/1905.04226/) (2019)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem](https://mlsanity.com/paper/1701.08376/) (2017)
- [Selective Sensor Fusion for Neural Visual-Inertial Odometry](https://mlsanity.com/paper/1903.01534/) (2019)
- [Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry](https://mlsanity.com/paper/1904.01892/) (2019)
- [Asynchronous Multi-View SLAM](https://mlsanity.com/paper/2101.06562/) (2021)
- [DeepVO: A Deep Learning approach for Monocular Visual Odometry](https://mlsanity.com/paper/1611.06069/) (2016)
- [Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning](https://mlsanity.com/paper/1903.10543/) (2019)
- [MDN-VO: Estimating Visual Odometry with Confidence](https://mlsanity.com/paper/2112.12812/) (2021)
- [Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation](https://mlsanity.com/paper/2112.12818/) (2021)

## Built on by (most cited first, 3 of 3)

- [Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach](https://mlsanity.com/paper/2305.06121/) (2023)
- [TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation](https://mlsanity.com/paper/2304.07728/) (2023)
- [Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation](https://mlsanity.com/paper/2403.14163/) (2024)

## Abstract (arXiv)

Motion estimation approaches typically employ sensor fusion techniques, such as the Kalman Filter, to handle individual sensor failures. More recently, deep learning-based fusion approaches have been proposed, increasing the performance and requiring less model-specific implementations. However, current deep fusion approaches often assume that sensors are synchronised, which is not always practical, especially for low-cost hardware. To address this limitation, in this work, we propose AFT-VO, a novel transformer-based sensor fusion architecture to estimate VO from multiple sensors. Our framework combines predictions from asynchronous multi-view cameras and accounts for the time discrepancies of measurements coming from different sources. Our approach first employs a Mixture Density Network (MDN) to estimate the probability distributions of the 6-DoF poses for every camera in the system. Then a novel transformer-based fusion module, AFT-VO, is introduced, which combines these asynchronous pose estimations, along with their confidences. More specifically, we introduce Discretiser and Source Encoding techniques which enable the fusion of multi-source asynchronous signals. We evaluate our approach on the popular nuScenes and KITTI datasets. Our experiments demonstrate that multi-view fusion for VO estimation provides robust and accurate trajectories, outperforming the state of the art in both challenging weather and lighting conditions.