# Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras

arXiv: https://arxiv.org/abs/2409.18673 · HTML: https://mlsanity.com/paper/2409.18673/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 27 Sep 2024.

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

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images](https://mlsanity.com/paper/2204.10776/) (2022)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://mlsanity.com/paper/1911.05932/) (2019)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)
- [DiffPoseNet: Direct Differentiable Camera Pose Estimation](https://mlsanity.com/paper/2203.11174/) (2022)
- [RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching](https://mlsanity.com/paper/2103.08573/) (2021)
- [Efficient Initial Pose-graph Generation for Global SfM](https://mlsanity.com/paper/2011.11986/) (2020)
- [Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching](https://mlsanity.com/paper/2102.04341/) (2021)
- [NeFSAC: Neurally Filtered Minimal Samples](https://mlsanity.com/paper/2207.07872/) (2022)
- [Structured Epipolar Matcher for Local Feature Matching](https://mlsanity.com/paper/2303.16646/) (2023)
- [Automatic Map Update Using Dashcam Videos](https://mlsanity.com/paper/2109.12131/) (2021)

## Built on by (most cited first, 1 of 1)

- [A prior information informed learning architecture for flying trajectory prediction](https://mlsanity.com/paper/2603.06863/) (2026)

## Abstract (arXiv)

Dashboard cameras (dashcams) record millions of driving videos daily, offering a valuable potential data source for various applications, including driving map production and updates. A necessary step for utilizing these dashcam data involves the estimation of camera poses. However, the low-quality images captured by dashcams, characterized by motion blurs and dynamic objects, pose challenges for existing image-matching methods in accurately estimating camera poses. In this study, we propose a precise pose estimation method for dashcam images, leveraging the inherent camera motion prior. Typically, image sequences captured by dash cameras exhibit pronounced motion prior, such as forward movement or lateral turns, which serve as essential cues for correspondence estimation. Building upon this observation, we devise a pose regression module aimed at learning camera motion prior, subsequently integrating these prior into both correspondences and pose estimation processes. The experiment shows that, in real dashcams dataset, our method is 22% better than the baseline for pose estimation in AUC5textdegree, and it can estimate poses for 19% more images with less reprojection error in Structure from Motion (SfM).