Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation

TL;DR

LiteLoc is an efficient visual localization method that reduces memory and computation by removing redundant features and condensing matches, achieving faster performance without sacrificing accuracy.

Contribution

The paper introduces a color-free, compact Gaussian scene representation and a match condensing strategy, significantly improving efficiency over previous methods.

Findings

Eliminates approximately 94% of redundant storage without losing localization accuracy.

Achieves nearly 19-fold speedup in dense pose estimation.

Outperforms previous state-of-the-art in multiple scenes with enhanced efficiency.

Abstract

This letter presents LiteLoc, a novel and efficient localizer built on 3D Gaussian Splatting (3DGS). The previous state-of-the-art (SoTA) sparse-to-dense localizer, STDLoc, has shown remarkable localization capability but suffers from severe storage redundancy and computational latency. By revisiting its design decisions, we derive two simple yet highly effective improvements that cumulatively make LiteLoc much more efficient in both memory and computation, while also being easier to train. One key observation is that the color field, inherited directly from Feature 3DGS, is functionally useless for localization. Yet, its reconstruction of high-frequency photometric details necessitates excessive Gaussian primitives, resulting in a tightly coupled color-feature representation with significant memory overhead and sub-optimal feature field optimization. To resolve this, we propose a color-free decoupled feature field that constructs a compact Gaussian scene representation by retaining only task-essential feature attributes, thereby eliminating approximately 94% of redundant storage with no loss of localization-relevant information. We further find that the primary computational bottleneck lies in the dense Perspective-n-Point (PnP) solver, where most matches contribute saturated geometric constraints with diminishing accuracy gains. Accordingly, we propose a condensing strategy that distills dense matches into a subset of 5% representative matches, enabling a nearly 19-fold speedup in robust estimation with negligible performance drop. Extensive experiments show that LiteLoc surpasses STDLoc in multiple scenes with considerable efficiency benefits, opening up exciting prospects for latency-sensitive visual localization.