# TACO: Trajectory Aligning Cross-view Optimisation

arXiv: https://arxiv.org/abs/2605.03315 · HTML: https://mlsanity.com/paper/2605.03315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 23 of 23)

- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping](https://mlsanity.com/paper/2007.00258/) (2020)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [Uncertainty-aware Vision-based Metric Cross-view Geolocalization](https://mlsanity.com/paper/2211.12145/) (2022)
- [SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation](https://mlsanity.com/paper/2211.14651/) (2022)
- [Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer](https://mlsanity.com/paper/2307.08015/) (2023)
- [Convolutional Cross-View Pose Estimation](https://mlsanity.com/paper/2303.05915/) (2023)
- [FG2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching](https://mlsanity.com/paper/2503.18725/) (2025)
- [UAV Pose Estimation using Cross-view Geolocalization with Satellite Imagery](https://mlsanity.com/paper/1809.05979/) (2018)
- [Continuous Self-Localization on Aerial Images Using Visual and Lidar Sensors](https://mlsanity.com/paper/2203.03334/) (2022)
- [BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation](https://mlsanity.com/paper/2312.15363/) (2023)
- [Increasing SLAM Pose Accuracy by Ground-to-Satellite Image Registration](https://mlsanity.com/paper/2404.09169/) (2024)
- [BEVRender: Vision-based Cross-view Vehicle Registration in Off-road GNSS-denied Environment](https://mlsanity.com/paper/2405.09001/) (2024)
- [PEnG: Pose-Enhanced Geo-Localisation](https://mlsanity.com/paper/2411.15742/) (2024)
- [Evaluation of Cross-View Matching to Improve Ground Vehicle Localization with Aerial Perception](https://mlsanity.com/paper/2003.06515/) (2020)

## Abstract (arXiv)

Cross-View Geo-localisation (CVGL) matches ground imagery against satellite tiles to give absolute position fixes, an alternative to GNSS where signals are occluded, jammed, or spoofed. Recent fine-grained CVGL methods regress sub-tile metric pose, but have only been evaluated as one-shot localisers, never as the primary fix in a live pipeline. Inertial sensing provides high-rate relative motion, but accumulates unbounded drift without an absolute anchor. We propose TACO, a tightly-coupled IMU + fine-grained CVGL pipeline that consumes a single GNSS reading at start-up and thereafter operates on onboard sensing alone. A closed-form cross-track error model triggers CVGL before IMU drift exceeds the matcher's capture radius, and a forward-biased five-point multi-crop search keeps inference cost fixed at five forward passes per fix. A yaw-residual gate rejects fixes that disagree with the onboard compass, and an anisotropic body-frame noise model scales each Unscented Kalman Filter update by per-fix confidence. A factor graph with vetted loop closures provides an offline smoothed trajectory. On the KITTI raw dataset, TACO reduces median Absolute Trajectory Error (ATE) from 97.0m (IMU-only) to 16.3m, a 5.9 times reduction, at <0.1 ms per-frame fusion cost and a 5-10% camera duty cycle. Code is available: github.com/tavisshore/TACO.