Towards Accurate Active Camera Localization

TL;DR

This paper introduces a novel active camera localization algorithm that combines passive and active modules to improve fine-scale camera pose accuracy in indoor scenes, outperforming existing Markov Localization methods.

Contribution

The proposed method integrates continuous pose optimization with scene uncertainty modeling, advancing active camera localization beyond traditional Markov-based approaches.

Findings

Outperforms state-of-the-art Markov Localization methods

Achieves higher accuracy in synthetic and real-world indoor scenes

Demonstrates robustness in challenging localization scenarios

Abstract

In this work, we tackle the problem of active camera localization, which controls the camera movements actively to achieve an accurate camera pose. The past solutions are mostly based on Markov Localization, which reduces the position-wise camera uncertainty for localization. These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale. We propose to overcome these limitations via a novel active camera localization algorithm, composed of a passive and an active localization module. The former optimizes the camera pose in the continuous pose space by establishing point-wise camera-world correspondences. The latter explicitly models the scene and camera uncertainty components to plan the right path for accurate camera pose estimation. We validate our algorithm on the challenging localization scenarios from both synthetic and scanned real-world indoor scenes. Experimental results demonstrate that our algorithm outperforms both the state-of-the-art Markov Localization based approach and other compared approaches on the fine-scale camera pose accuracy. Code and data are released at https://github.com/qhFang/AccurateACL.