PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization
Yanan Zhou, Zhaoyan Qian, Yanli Li, Nan Yang, Zhongliang Guo, Dong Yuan

TL;DR
PoseCompass introduces an intelligent pose selection method that enhances synthetic data quality for visual localization, significantly improving accuracy and reducing adaptation time.
Contribution
It proposes a novel value-based pose ranking mechanism for synthetic view selection, improving APR performance with efficient data augmentation.
Findings
Reduces adaptation time from 15.2 to 5.1 minutes.
Cuts median pose errors by 53.8%.
Outperforms random baseline methods.
Abstract
In visual localization, Absolute Pose Regression (APR) enables real-time 6-DoF camera pose inference from single images, yet critically depends on fine-tuning data quality and coverage. While recent methods leverage 3D Gaussian Splatting (3DGS) for novel view synthesis-based data augmentation, random sampling generates redundant views and noisy samples from poorly reconstructed regions. To mitigate this research gap, we propose PoseCompass, an intelligent pose selection pipeline for 3DGS-based APR. PoseCompass formulates synthetic pose selection and derives a value-based pose ranking mechanism to identify informative poses. The ranking integrates three dimensions: Localization Difficulty, favoring challenging regions; Coverage Novelty, exploring under-sampled areas; and Rendering Observability, filtering artifacts and noise. PoseCompass then generates trajectory-constrained candidates,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
