# IONext: Unlocking the Next Era of Inertial Odometry

arXiv: https://arxiv.org/abs/2507.17089 · HTML: https://mlsanity.com/paper/2507.17089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Inception Transformer](https://mlsanity.com/paper/2205.12956/) (2022)
- [InceptionNeXt: When Inception Meets ConvNeXt](https://mlsanity.com/paper/2303.16900/) (2023)
- [RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods](https://mlsanity.com/paper/1905.12853/) (2019)
- [On the Connection between Local Attention and Dynamic Depth-wise Convolution](https://mlsanity.com/paper/2106.04263/) (2021)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [IONet: Learning to Cure the Curse of Drift in Inertial Odometry](https://mlsanity.com/paper/1802.02209/) (2018)
- [TLIO: Tight Learned Inertial Odometry](https://mlsanity.com/paper/2007.01867/) (2020)
- [RIDI: Robust IMU Double Integration](https://mlsanity.com/paper/1712.09004/) (2017)
- [IDOL: A Framework for IMU-DVS Odometry using Lines](https://mlsanity.com/paper/2008.05749/) (2020)
- [OxIOD: The Dataset for Deep Inertial Odometry](https://mlsanity.com/paper/1809.07491/) (2018)
- [TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition](https://mlsanity.com/paper/2310.19380/) (2023)
- [RIO: Rotation-equivariance supervised learning of robust inertial odometry](https://mlsanity.com/paper/2111.11676/) (2021)
- [Neural Inertial Localization](https://mlsanity.com/paper/2203.15851/) (2022)
- [CTIN: Robust Contextual Transformer Network for Inertial Navigation](https://mlsanity.com/paper/2112.02143/) (2021)
- [EqNIO: Subequivariant Neural Inertial Odometry](https://mlsanity.com/paper/2408.06321/) (2024)
- [AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability](https://mlsanity.com/paper/2501.15659/) (2025)
- [iMoT: Inertial Motion Transformer for Inertial Navigation](https://mlsanity.com/paper/2412.12190/) (2024)
- [Wavelet Dynamic Selection Network for Inertial Sensor Signal Enhancement](https://mlsanity.com/paper/2401.05416/) (2023)

## Abstract (arXiv)

Researchers have increasingly adopted Transformer-based models for inertial odometry. While Transformers excel at modeling long-range dependencies, their limited sensitivity to local, fine-grained motion variations and lack of inherent inductive biases often hinder localization accuracy and generalization. Recent studies have shown that incorporating large-kernel convolutions and Transformer-inspired architectural designs into CNN can effectively expand the receptive field, thereby improving global motion perception. Motivated by these insights, we propose a novel CNN-based module called the Dual-wing Adaptive Dynamic Mixer (DADM), which adaptively captures both global motion patterns and local, fine-grained motion features from dynamic inputs. This module dynamically generates selective weights based on the input, enabling efficient multi-scale feature aggregation. To further improve temporal modeling, we introduce the Spatio-Temporal Gating Unit (STGU), which selectively extracts representative and task-relevant motion features in the temporal domain. This unit addresses the limitations of temporal modeling observed in existing CNN approaches. Built upon DADM and STGU, we present a new CNN-based inertial odometry backbone, named Next Era of Inertial Odometry (IONext). Extensive experiments on six public datasets demonstrate that IONext consistently outperforms state-of-the-art (SOTA) Transformer- and CNN-based methods. For instance, on the RNIN dataset, IONext reduces the average ATE by 10% and the average RTE by 12% compared to the representative model iMOT.