SREF: Semantics-Refined Feature Extraction for Long-Term Visual Localization

TL;DR

This paper introduces a new method for visual localization that improves accuracy and robustness in changing environments by using refined semantic features.

Contribution

The novel contribution is a semantics-guided feature extraction framework that enhances stability and suppresses dynamic disturbances.

Findings

The proposed framework achieves state-of-the-art accuracy and robustness in visual localization.

It demonstrates strong performance on Aachen and RobotCar-Seasons benchmarks under various conditions.

The method effectively bridges coarse semantic guidance with fine-grained stability estimation.

Abstract

Accurate and robust visual localization under changing environments remains a fundamental challenge in autonomous driving and mobile robotics. Traditional handcrafted features often degrade under long-term illumination and viewpoint variations, while recent CNN-based methods, although more robust, typically rely on coarse semantic cues and remain vulnerable to dynamic objects. In this paper, we propose a fine-grained semantics-guided feature extraction framework that adaptively selects stable keypoints while suppressing dynamic disturbances. A fine-grained semantic refinement module subdivides coarse semantic categories into stability-homogeneous sub-classes, and a dual-attention mechanism enhances local repeatability and semantic consistency. By integrating physical priors with self-supervised clustering, the proposed framework learns discriminative and reliable feature representations. Extensive experiments on the Aachen and RobotCar-Seasons benchmarks demonstrate that the proposed approach achieves state-of-the-art accuracy and robustness while maintaining real-time efficiency, effectively bridging coarse semantic guidance with fine-grained stability estimation. Quantitatively, our method achieves strong localization performance on Aachen (up to 88.1% at night under the (0.2°,0.25 m) threshold) and on RobotCar-Seasons (up to 57.2%/28.4% under the same threshold for day/night), demonstrating improved robustness to seasonal and illumination changes.

Figures