Absolute Pose Regression (APR) predicts 6D camera poses but lacks the adaptability to unknown environments without retraining, while Relative Pose Regression (RPR) generalizes better yet requires a large image retrieval database. Visual Odometry (VO) generalizes well in unseen environments but suffers from accumulated error in open trajectories. To address this dilemma, we introduce a new task, Scene-agnostic Pose Regression (SPR), which can achieve accurate pose regression in a flexible way while eliminating the need for retraining or databases. To benchmark SPR, we created a large-scale dataset, 360SPR, with over 200K photorealistic panoramas, 3.6M pinhole images and camera poses in 270 scenes at three different sensor heights. Furthermore, a SPR-Mamba model is initially proposed to address SPR in a dual-branch manner. Extensive experiments and studies demonstrate the effectiveness of our SPR paradigm, dataset, and model. In the unknown scenes of both 360SPR and 360Loc datasets, our method consistently outperforms APR, RPR and VO. The dataset and code are available at https://junweizheng93.github.io/publications/SPR/SPR.html.
@article{arxiv.2503.19543,
title = {Scene-agnostic Pose Regression for Visual Localization},
author = {Junwei Zheng and Ruiping Liu and Yufan Chen and Zhenfang Chen and Kailun Yang and Jiaming Zhang and Rainer Stiefelhagen},
journal= {arXiv preprint arXiv:2503.19543},
year = {2025}
}
Comments
Accepted by CVPR 2025. Project page: https://junweizheng93.github.io/publications/SPR/SPR.html