ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting

TL;DR

ULF-Loc introduces an unbiased landmark feature framework for robust visual localization, addressing biases in Gaussian feature learning and achieving improved accuracy and efficiency over state-of-the-art methods.

Contribution

The paper reveals inherent biases in 3D Gaussian Splatting features and proposes ULF-Loc, a novel framework that enhances localization accuracy and efficiency.

Findings

Reduces median translation error by 17% on Cambridge Landmarks

Achieves 1/10 training time of STDLoc

Uses 1/6 GPU memory compared to STDLoc

Abstract

Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with feature-based localization. These methods rely on direct matching between 2D query features and the 3D Gaussian feature field, but this often results in mismatches due to an inherent bias in the learned Gaussian feature. We theoretically analyze the feature learning process in 3DGS, revealing that the widely adopted $\alpha$-blending optimization inherently introduces bias into 3D point features. This bias stems from the entanglement between individual Gaussians and their neighboring Gaussians, making the learned features unsuitable for precise matching tasks. Motivated by these findings, we propose ULF-Loc, an unbiased landmark feature framework that replaces biased feature optimization with geometry-weighted feature fusion. We further introduce keypoint-consensus landmark sampling to select reliable Gaussians and local geometric consistency verification to reject mismatches caused by rendering artifacts. On the Cambridge Landmarks dataset, ULF-Loc reduces the mean median translation error by 17\% compared to the state-of-the-art, while achieving superior efficiency with only 1/10 the training time and 1/6 the GPU memory of STDLoc.